Update README.md

README.md

@@ -57,8 +57,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: ant_v4
+          name: ant_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 6315.00 +/- 675.00
@@ -70,8 +70,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: halfcheetah_v4
+          name: halfcheetah_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 7226.50 +/- 241.50
@@ -83,8 +83,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: hopper_v4
+          name: hopper_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 2794.60 +/- 612.62
@@ -96,8 +96,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: humanoid_v4
+          name: humanoid_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 7376.26 +/- 0.00
@@ -109,8 +109,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: humanoidstandup_v4
+          name: humanoidstandup_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 320567.82 +/- 58462.11
@@ -122,8 +122,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: inverteddoublependulum_v4
+          name: inverteddoublependulum_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 6105.75 +/- 4368.65
@@ -135,8 +135,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: invertedpendulum_v4
+          name: invertedpendulum_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 1000.00 +/- 0.00
@@ -148,8 +148,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: pusher_v4
+          name: pusher_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: -37.82 +/- 8.72
@@ -161,8 +161,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: reacher_v4
+          name: reacher_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: -6.25 +/- 2.63
@@ -174,8 +174,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: swimmer_v4
+          name: swimmer_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 93.20 +/- 5.40
@@ -187,8 +187,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: MuJoCo
-          type: walker2d_v4
+          name: walker2d_v4
+          type: MuJoCo
         metrics:
           - type: total_reward
             value: 5400.00 +/- 107.95
@@ -200,8 +200,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: assembly-v2
+          name: assembly-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 307.08 +/- 25.20
@@ -213,8 +213,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: basketball-v2
+          name: basketball-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 568.04 +/- 60.72
@@ -226,8 +226,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: bin-picking-v2
+          name: bin-picking-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 7.88 +/- 4.28
@@ -239,8 +239,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: box-close-v2
+          name: box-close-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 61.75 +/- 13.54
@@ -252,8 +252,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: button-press-v2
+          name: button-press-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 624.67 +/- 42.77
@@ -265,8 +265,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: button-press-topdown-v2
+          name: button-press-topdown-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 449.36 +/- 62.16
@@ -278,8 +278,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: button-press-topdown-wall-v2
+          name: button-press-topdown-wall-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 482.08 +/- 32.48
@@ -291,8 +291,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: button-press-wall-v2
+          name: button-press-wall-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 672.00 +/- 26.48
@@ -304,8 +304,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: coffee-button-v2
+          name: coffee-button-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 719.00 +/- 41.10
@@ -317,8 +317,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: coffee-pull-v2
+          name: coffee-pull-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 26.04 +/- 56.12
@@ -330,8 +330,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: coffee-push-v2
+          name: coffee-push-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 571.01 +/- 112.28
@@ -343,8 +343,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: dial-turn-v2
+          name: dial-turn-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 783.90 +/- 53.17
@@ -356,8 +356,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: disassemble-v2
+          name: disassemble-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 523.60 +/- 58.15
@@ -369,8 +369,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: door-close-v2
+          name: door-close-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 538.10 +/- 25.76
@@ -382,8 +382,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: door-lock-v2
+          name: door-lock-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 356.51 +/- 249.44
@@ -395,8 +395,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: door-open-v2
+          name: door-open-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 581.33 +/- 26.33
@@ -408,8 +408,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: door-unlock-v2
+          name: door-unlock-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 352.86 +/- 147.78
@@ -421,8 +421,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: drawer-close-v2
+          name: drawer-close-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 838.88 +/- 7.41
@@ -434,8 +434,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: drawer-open-v2
+          name: drawer-open-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 493.00 +/- 3.57
@@ -447,8 +447,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: faucet-close-v2
+          name: faucet-close-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 749.46 +/- 14.83
@@ -460,8 +460,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: faucet-open-v2
+          name: faucet-open-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 732.47 +/- 15.23
@@ -473,8 +473,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: hammer-v2
+          name: hammer-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 669.31 +/- 69.56
@@ -486,8 +486,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: hand-insert-v2
+          name: hand-insert-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 142.81 +/- 146.64
@@ -499,8 +499,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: handle-press-v2
+          name: handle-press-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 835.30 +/- 114.19
@@ -512,8 +512,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: handle-press-side-v2
+          name: handle-press-side-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 852.96 +/- 16.08
@@ -525,8 +525,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: handle-pull-v2
+          name: handle-pull-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 701.10 +/- 13.82
@@ -538,8 +538,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: handle-pull-side-v2
+          name: handle-pull-side-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 493.10 +/- 53.65
@@ -551,8 +551,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: lever-pull-v2
+          name: lever-pull-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 548.72 +/- 81.12
@@ -564,8 +564,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: peg-insert-side-v2
+          name: peg-insert-side-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 352.43 +/- 137.24
@@ -577,8 +577,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: peg-unplug-side-v2
+          name: peg-unplug-side-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 401.52 +/- 175.27
@@ -590,8 +590,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: pick-out-of-hole-v2
+          name: pick-out-of-hole-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 364.20 +/- 79.56
@@ -603,8 +603,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: pick-place-v2
+          name: pick-place-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 414.02 +/- 91.10
@@ -616,8 +616,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: pick-place-wall-v2
+          name: pick-place-wall-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 553.18 +/- 84.72
@@ -629,8 +629,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: plate-slide-v2
+          name: plate-slide-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 531.98 +/- 156.94
@@ -642,8 +642,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: plate-slide-back-v2
+          name: plate-slide-back-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 703.93 +/- 108.27
@@ -655,8 +655,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: plate-slide-back-side-v2
+          name: plate-slide-back-side-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 721.29 +/- 62.15
@@ -668,8 +668,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: plate-slide-side-v2
+          name: plate-slide-side-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 578.24 +/- 143.73
@@ -681,8 +681,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: push-v2
+          name: push-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 729.33 +/- 104.40
@@ -694,8 +694,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: push-back-v2
+          name: push-back-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 372.16 +/- 112.75
@@ -707,8 +707,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: push-wall-v2
+          name: push-wall-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 741.68 +/- 14.84
@@ -720,8 +720,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: reach-v2
+          name: reach-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 684.45 +/- 136.55
@@ -733,8 +733,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: reach-wall-v2
+          name: reach-wall-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 738.02 +/- 100.96
@@ -746,8 +746,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: shelf-place-v2
+          name: shelf-place-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 268.34 +/- 29.07
@@ -759,8 +759,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: soccer-v2
+          name: soccer-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 438.44 +/- 189.63
@@ -772,8 +772,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: stick-pull-v2
+          name: stick-pull-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 483.98 +/- 83.25
@@ -785,8 +785,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: stick-push-v2
+          name: stick-push-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 563.07 +/- 173.40
@@ -798,8 +798,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: sweep-v2
+          name: sweep-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 487.19 +/- 60.02
@@ -811,8 +811,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: sweep-into-v2
+          name: sweep-into-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 798.80 +/- 15.62
@@ -824,8 +824,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: window-close-v2
+          name: window-close-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 562.48 +/- 91.17
@@ -837,8 +837,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Meta-World
-          type: window-open-v2
+          name: window-open-v2
+          type: Meta-World
         metrics:
           - type: total_reward
             value: 573.69 +/- 93.98
@@ -850,8 +850,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandblockstack
+          name: shadowhandblockstack
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 347.40 +/- 50.60
@@ -863,8 +863,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandbottlecap
+          name: shadowhandbottlecap
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 338.25 +/- 81.25
@@ -876,8 +876,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandcatchabreast
+          name: shadowhandcatchabreast
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 11.81 +/- 21.28
@@ -889,8 +889,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandcatchover2underarm
+          name: shadowhandcatchover2underarm
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 31.60 +/- 7.20
@@ -902,8 +902,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandcatchunderarm
+          name: shadowhandcatchunderarm
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 18.21 +/- 9.46
@@ -915,8 +915,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhanddoorcloseinward
+          name: shadowhanddoorcloseinward
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 3.97 +/- 0.15
@@ -928,8 +928,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhanddoorcloseoutward
+          name: shadowhanddoorcloseoutward
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 358.50 +/- 4.50
@@ -941,8 +941,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhanddooropeninward
+          name: shadowhanddooropeninward
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 108.25 +/- 8.50
@@ -954,8 +954,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhanddooropenoutward
+          name: shadowhanddooropenoutward
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 83.65 +/- 12.10
@@ -967,8 +967,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandgraspandplace
+          name: shadowhandgraspandplace
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 485.15 +/- 89.10
@@ -980,8 +980,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandkettle
+          name: shadowhandkettle
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: -450.47 +/- 0.00
@@ -993,8 +993,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandliftunderarm
+          name: shadowhandliftunderarm
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 377.92 +/- 13.24
@@ -1006,8 +1006,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandover
+          name: shadowhandover
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 33.01 +/- 0.96
@@ -1019,8 +1019,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandpen
+          name: shadowhandpen
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 98.80 +/- 83.60
@@ -1032,8 +1032,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandpushblock
+          name: shadowhandpushblock
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 445.60 +/- 2.20
@@ -1045,8 +1045,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandreorientation
+          name: shadowhandreorientation
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 2798.00 +/- 2112.00
@@ -1058,8 +1058,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandscissors
+          name: shadowhandscissors
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 747.95 +/- 7.65
@@ -1071,8 +1071,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandswingcup
+          name: shadowhandswingcup
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 3775.50 +/- 583.70
@@ -1084,8 +1084,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandswitch
+          name: shadowhandswitch
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 268.25 +/- 2.35
@@ -1097,8 +1097,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Bi-DexHands
-          type: shadowhandtwocatchunderarm
+          name: shadowhandtwocatchunderarm
+          type: Bi-DexHands
         metrics:
           - type: total_reward
             value: 2.17 +/- 0.67
@@ -1110,8 +1110,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-0-v1
+          name: industrial-benchmark-0-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -191.39 +/- 22.96
@@ -1123,8 +1123,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-5-v1
+          name: industrial-benchmark-5-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -194.01 +/- 3.66
@@ -1136,8 +1136,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-10-v1
+          name: industrial-benchmark-10-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -213.28 +/- 2.01
@@ -1149,8 +1149,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-15-v1
+          name: industrial-benchmark-15-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -227.82 +/- 4.29
@@ -1162,8 +1162,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-20-v1
+          name: industrial-benchmark-20-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -259.99 +/- 22.70
@@ -1175,8 +1175,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-25-v1
+          name: industrial-benchmark-25-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -282.28 +/- 20.70
@@ -1188,8 +1188,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-30-v1
+          name: industrial-benchmark-30-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -307.02 +/- 19.23
@@ -1201,8 +1201,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-35-v1
+          name: industrial-benchmark-35-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -314.36 +/- 5.62
@@ -1214,8 +1214,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-40-v1
+          name: industrial-benchmark-40-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -339.34 +/- 9.57
@@ -1227,8 +1227,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-45-v1
+          name: industrial-benchmark-45-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -366.63 +/- 7.47
@@ -1240,8 +1240,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-50-v1
+          name: industrial-benchmark-50-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -395.94 +/- 17.65
@@ -1253,8 +1253,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-55-v1
+          name: industrial-benchmark-55-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -403.73 +/- 2.03
@@ -1266,8 +1266,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-60-v1
+          name: industrial-benchmark-60-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -434.25 +/- 4.12
@@ -1279,8 +1279,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-65-v1
+          name: industrial-benchmark-65-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -480.31 +/- 8.63
@@ -1292,8 +1292,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-70-v1
+          name: industrial-benchmark-70-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -480.76 +/- 5.98
@@ -1305,8 +1305,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-75-v1
+          name: industrial-benchmark-75-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -476.83 +/- 2.44
@@ -1318,8 +1318,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-80-v1
+          name: industrial-benchmark-80-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -497.13 +/- 2.95
@@ -1331,8 +1331,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-85-v1
+          name: industrial-benchmark-85-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -513.83 +/- 3.06
@@ -1344,8 +1344,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-90-v1
+          name: industrial-benchmark-90-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -532.70 +/- 3.61
@@ -1357,8 +1357,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-95-v1
+          name: industrial-benchmark-95-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -557.42 +/- 3.81
@@ -1370,8 +1370,8 @@ model-index:
           type: in-context-reinforcement-learning
           name: In-Context Reinforcement Learning
         dataset:
-          name: Industrial-Benchmark
-          type: industrial-benchmark-100-v1
+          name: industrial-benchmark-100-v1
+          type: Industrial-Benchmark
         metrics:
           - type: total_reward
             value: -574.57 +/- 4.37