| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.17025338113307953, | |
| "min": 0.14944949746131897, | |
| "max": 1.386743187904358, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 5044.9482421875, | |
| "min": 4423.705078125, | |
| "max": 42068.2421875, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999968.0, | |
| "min": 29952.0, | |
| "max": 2999968.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999968.0, | |
| "min": 29952.0, | |
| "max": 2999968.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.8172018527984619, | |
| "min": -0.13209950923919678, | |
| "max": 0.8467546105384827, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 241.89175415039062, | |
| "min": -31.835981369018555, | |
| "max": 256.9213562011719, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.020818013697862625, | |
| "min": -0.022503165528178215, | |
| "max": 0.4203815460205078, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 6.162132263183594, | |
| "min": -6.458408355712891, | |
| "max": 99.63042449951172, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06577292206283245, | |
| "min": 0.0636873666342336, | |
| "max": 0.07395852262492379, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9865938309424868, | |
| "min": 0.5071982691034704, | |
| "max": 1.0963826900115237, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.01426170475056602, | |
| "min": 0.000149989346062057, | |
| "max": 0.017842259141616523, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.21392557125849032, | |
| "min": 0.001649882806682627, | |
| "max": 0.24979162798263133, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 1.4759728413755528e-06, | |
| "min": 1.4759728413755528e-06, | |
| "max": 0.00029838354339596195, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 2.213959262063329e-05, | |
| "min": 2.213959262063329e-05, | |
| "max": 0.0038017656327448326, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1004919577777778, | |
| "min": 0.1004919577777778, | |
| "max": 0.19946118095238097, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.5073793666666668, | |
| "min": 1.3962282666666668, | |
| "max": 2.7225542333333337, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 5.914658199999991e-05, | |
| "min": 5.914658199999991e-05, | |
| "max": 0.009946171977142856, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0008871987299999987, | |
| "min": 0.0008871987299999987, | |
| "max": 0.12673879115000003, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.00632007559761405, | |
| "min": 0.006142762023955584, | |
| "max": 0.40981340408325195, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.09480113536119461, | |
| "min": 0.08599866926670074, | |
| "max": 2.8686938285827637, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 224.390625, | |
| "min": 211.42857142857142, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 28722.0, | |
| "min": 15984.0, | |
| "max": 33251.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.7752968621207401, | |
| "min": -1.0000000521540642, | |
| "max": 1.789630117889953, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 227.23799835145473, | |
| "min": -30.999001622200012, | |
| "max": 261.28599721193314, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.7752968621207401, | |
| "min": -1.0000000521540642, | |
| "max": 1.789630117889953, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 227.23799835145473, | |
| "min": -30.999001622200012, | |
| "max": 261.28599721193314, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.014845759210970755, | |
| "min": 0.014325044185095802, | |
| "max": 7.842225390486419, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 1.9002571790042566, | |
| "min": 1.8713174743461423, | |
| "max": 125.47560624778271, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1679295953", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/opt/conda/envs/ml2/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", | |
| "mlagents_version": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.11.0+cu115", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1679302586" | |
| }, | |
| "total": 6632.613298296994, | |
| "count": 1, | |
| "self": 0.5290249379977467, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.015625788997567724, | |
| "count": 1, | |
| "self": 0.015625788997567724 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 6632.068647569999, | |
| "count": 1, | |
| "self": 5.153155992193206, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 6.332068398995034, | |
| "count": 1, | |
| "self": 6.332068398995034 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 6620.427630555794, | |
| "count": 194960, | |
| "self": 5.296379827304918, | |
| "children": { | |
| "env_step": { | |
| "total": 4270.302283916091, | |
| "count": 194960, | |
| "self": 3481.912998950298, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 785.1104840326007, | |
| "count": 194960, | |
| "self": 16.8415160821678, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 768.2689679504329, | |
| "count": 187543, | |
| "self": 768.2689679504329 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 3.2788009331925423, | |
| "count": 194960, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 6621.544129394875, | |
| "count": 194960, | |
| "is_parallel": true, | |
| "self": 3452.1718441081684, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0012210179993417114, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000425993996032048, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0007950240033096634, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0007950240033096634 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.049499485998239834, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003418380001676269, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0006594250007765368, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006594250007765368 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.047462796996114776, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.047462796996114776 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0010354260011808947, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00035914600448450074, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0006762799966963939, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0006762799966963939 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 3169.3722852867068, | |
| "count": 194959, | |
| "is_parallel": true, | |
| "self": 47.82474687942886, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 33.71205294635729, | |
| "count": 194959, | |
| "is_parallel": true, | |
| "self": 33.71205294635729 | |
| }, | |
| "communicator.exchange": { | |
| "total": 2965.6195591329015, | |
| "count": 194959, | |
| "is_parallel": true, | |
| "self": 2965.6195591329015 | |
| }, | |
| "steps_from_proto": { | |
| "total": 122.21592632801912, | |
| "count": 194959, | |
| "is_parallel": true, | |
| "self": 31.40662391592923, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 90.80930241208989, | |
| "count": 1559672, | |
| "is_parallel": true, | |
| "self": 90.80930241208989 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 2344.828966812398, | |
| "count": 194960, | |
| "self": 10.43267517080676, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 436.7336316047804, | |
| "count": 194960, | |
| "self": 435.89596089776023, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.8376707070201519, | |
| "count": 6, | |
| "self": 0.8376707070201519 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1897.6626600368108, | |
| "count": 1392, | |
| "self": 937.7853251422348, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 959.877334894576, | |
| "count": 68448, | |
| "self": 959.877334894576 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 4.024012014269829e-06, | |
| "count": 1, | |
| "self": 4.024012014269829e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.1557885990041541, | |
| "count": 1, | |
| "self": 0.005362676005461253, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.15042592299869284, | |
| "count": 1, | |
| "self": 0.15042592299869284 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |