{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1812715381383896, "min": 0.1697080135345459, "max": 1.6065279245376587, "count": 200 }, "Pyramids.Policy.Entropy.sum": { "value": 1864.9215087890625, "min": 1685.9420166015625, "max": 16450.845703125, "count": 200 }, "Pyramids.Step.mean": { "value": 1999988.0, "min": 9984.0, "max": 1999988.0, "count": 200 }, "Pyramids.Step.sum": { "value": 1999988.0, "min": 9984.0, "max": 1999988.0, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7763552069664001, "min": -0.08807287365198135, "max": 0.8628113269805908, "count": 200 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.6355209350586, "min": -7.045829772949219, "max": 89.73237609863281, "count": 200 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.12793628871440887, "min": 0.1241626963019371, "max": 3.223942279815674, "count": 200 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.793628692626953, "min": 11.833174705505371, "max": 256.96441650390625, "count": 200 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07152327620079396, "min": 0.05934585555951344, "max": 0.08020872884755215, "count": 200 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.14304655240158792, "min": 0.05934585555951344, "max": 0.1604174576951043, "count": 200 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016820931834262358, "min": 0.0004981905462955183, "max": 1.2856630093107622, "count": 200 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.033641863668524716, "min": 0.0004981905462955183, "max": 1.2856630093107622, "count": 200 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.469997176999891e-07, "min": 8.469997176999891e-07, "max": 0.0002987712004096, "count": 200 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.6939994353999782e-06, "min": 1.6939994353999782e-06, "max": 0.0005687616104127999, "count": 200 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10028230000000002, "min": 0.10028230000000002, "max": 0.19959039999999997, "count": 200 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.20056460000000004, "min": 0.10089415000000002, "max": 0.3895872, "count": 200 }, "Pyramids.Policy.Beta.mean": { "value": 3.820176999999964e-05, "min": 3.820176999999964e-05, "max": 0.009959080960000002, "count": 200 }, "Pyramids.Policy.Beta.sum": { "value": 7.640353999999929e-05, "min": 7.640353999999929e-05, "max": 0.01895976128, "count": 200 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01132755633443594, "min": 0.010952742770314217, "max": 0.7967495918273926, "count": 200 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.02265511266887188, "min": 0.011068697087466717, "max": 0.7967495918273926, "count": 200 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 226.30434782608697, "min": 210.06521739130434, "max": 999.0, "count": 196 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 10410.0, "min": 406.0, "max": 15984.0, "count": 196 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7759361599988126, "min": -1.0000000521540642, "max": 1.7878297776617902, "count": 197 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.46899951994419, "min": -16.000000834465027, "max": 88.86559921503067, "count": 197 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7759361599988126, "min": -1.0000000521540642, "max": 1.7878297776617902, "count": 197 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.46899951994419, "min": -16.000000834465027, "max": 88.86559921503067, "count": 197 }, "Pyramids.Policy.RndReward.mean": { "value": 0.2671700805930936, "min": 0.24556314122552672, "max": 115.93597248196602, "count": 197 }, "Pyramids.Policy.RndReward.sum": { "value": 12.556993787875399, "min": 3.919705420732498, "max": 1854.9755597114563, "count": 197 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728489636", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training_4 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728495200" }, "total": 5563.281154713, "count": 1, "self": 0.578380326000115, "children": { "run_training.setup": { "total": 0.06315506800001458, "count": 1, "self": 0.06315506800001458 }, "TrainerController.start_learning": { "total": 5562.639619319, "count": 1, "self": 3.658621601048253, "children": { "TrainerController._reset_env": { "total": 2.3372126550002577, "count": 1, "self": 2.3372126550002577 }, "TrainerController.advance": { "total": 5556.585015841953, "count": 129381, "self": 3.7074042090926014, "children": { "env_step": { "total": 3966.0238739530296, "count": 129381, "self": 3736.5980412040853, "children": { "SubprocessEnvManager._take_step": { "total": 227.22686251303276, "count": 129381, "self": 10.69970989295598, "children": { "TorchPolicy.evaluate": { "total": 216.52715262007678, "count": 125067, "self": 216.52715262007678 } } }, "workers": { "total": 2.1989702359114744, "count": 129381, "self": 0.0, "children": { "worker_root": { "total": 5551.047635885227, "count": 129381, "is_parallel": true, "self": 2103.7738006034288, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028710380001939484, "count": 1, "is_parallel": true, "self": 0.0008379179998883046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020331200003056438, "count": 8, "is_parallel": true, "self": 0.0020331200003056438 } } }, "UnityEnvironment.step": { "total": 0.08737620700048865, "count": 1, "is_parallel": true, "self": 0.0008961279991126503, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005002860007152776, "count": 1, "is_parallel": true, "self": 0.0005002860007152776 }, "communicator.exchange": { "total": 0.08327173799989396, "count": 1, "is_parallel": true, "self": 0.08327173799989396 }, "steps_from_proto": { "total": 0.0027080550007667625, "count": 1, "is_parallel": true, "self": 0.00039993899918044917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023081160015863134, "count": 8, "is_parallel": true, "self": 0.0023081160015863134 } } } } } } }, "UnityEnvironment.step": { "total": 3447.273835281798, "count": 129380, "is_parallel": true, "self": 81.91633728868419, "children": { "UnityEnvironment._generate_step_input": { "total": 53.13809518709877, "count": 129380, "is_parallel": true, "self": 53.13809518709877 }, "communicator.exchange": { "total": 3082.081615678245, "count": 129380, "is_parallel": true, "self": 3082.081615678245 }, "steps_from_proto": { "total": 230.13778712777003, "count": 129380, "is_parallel": true, "self": 49.45365916853552, "children": { "_process_rank_one_or_two_observation": { "total": 180.6841279592345, "count": 1035040, "is_parallel": true, "self": 180.6841279592345 } } } } } } } } } } }, "trainer_advance": { "total": 1586.8537376798304, "count": 129381, "self": 6.444372039120935, "children": { "process_trajectory": { "total": 284.3386811197315, "count": 129381, "self": 284.0804185877314, "children": { "RLTrainer._checkpoint": { "total": 0.25826253200011706, "count": 4, "self": 0.25826253200011706 } } }, "_update_policy": { "total": 1296.070684520978, "count": 242, "self": 663.0619838800121, "children": { "TorchPPOOptimizer.update": { "total": 633.0087006409658, "count": 46473, "self": 633.0087006409658 } } } } } } }, "trainer_threads": { "total": 1.0690000635804608e-06, "count": 1, "self": 1.0690000635804608e-06 }, "TrainerController._save_models": { "total": 0.058768151999174734, "count": 1, "self": 0.0011314740004308987, "children": { "RLTrainer._checkpoint": { "total": 0.057636677998743835, "count": 1, "self": 0.057636677998743835 } } } } } } }