| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.3928498029708862, | |
| "min": 1.21998131275177, | |
| "max": 3.2957465648651123, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 25985.005859375, | |
| "min": 19855.798828125, | |
| "max": 145768.640625, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 50.73684210526316, | |
| "min": 40.84166666666667, | |
| "max": 999.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19280.0, | |
| "min": 11988.0, | |
| "max": 25676.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1699.0914227549324, | |
| "min": 1189.972434065279, | |
| "max": 1749.382347266285, | |
| "count": 4983 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 322827.37032343715, | |
| "min": 2381.187981918631, | |
| "max": 409040.2887565867, | |
| "count": 4983 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 49999944.0, | |
| "min": 9644.0, | |
| "max": 49999944.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 49999944.0, | |
| "min": 9644.0, | |
| "max": 49999944.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.024136614054441452, | |
| "min": -0.13468629121780396, | |
| "max": 0.20137563347816467, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 4.585956573486328, | |
| "min": -21.906532287597656, | |
| "max": 41.282005310058594, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.027685396373271942, | |
| "min": -0.13594380021095276, | |
| "max": 0.19884014129638672, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 5.260225296020508, | |
| "min": -21.36837387084961, | |
| "max": 40.762229919433594, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.0655136836202521, | |
| "min": -0.5540761890865508, | |
| "max": 0.4387761607075369, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 12.4475998878479, | |
| "min": -65.62940013408661, | |
| "max": 70.40700006484985, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.0655136836202521, | |
| "min": -0.5540761890865508, | |
| "max": 0.4387761607075369, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 12.4475998878479, | |
| "min": -65.62940013408661, | |
| "max": 70.40700006484985, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 5000 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.018493753513515305, | |
| "min": 0.010254121795878746, | |
| "max": 0.025699365340794127, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.018493753513515305, | |
| "min": 0.010254121795878746, | |
| "max": 0.025699365340794127, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.10656784797708194, | |
| "min": 3.3563168168863435e-05, | |
| "max": 0.1264787902434667, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.10656784797708194, | |
| "min": 3.3563168168863435e-05, | |
| "max": 0.1264787902434667, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.10796791364749272, | |
| "min": 3.787727546296082e-05, | |
| "max": 0.12967853769659995, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.10796791364749272, | |
| "min": 3.787727546296082e-05, | |
| "max": 0.12967853769659995, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000004, | |
| "max": 0.20000000000000007, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 2424 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 2424 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1714137260", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/home/nick/anaconda3/envs/unity/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.2+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1714169189" | |
| }, | |
| "total": 31928.723726832017, | |
| "count": 1, | |
| "self": 0.16680422102217562, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.046483440994052216, | |
| "count": 1, | |
| "self": 0.046483440994052216 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 31928.51043917, | |
| "count": 1, | |
| "self": 22.269319675542647, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 2.9984970330551732, | |
| "count": 250, | |
| "self": 2.9984970330551732 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 31903.14578121141, | |
| "count": 3448211, | |
| "self": 22.521499714057427, | |
| "children": { | |
| "env_step": { | |
| "total": 23975.74121089111, | |
| "count": 3448211, | |
| "self": 18339.036810970196, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 5621.8259733981395, | |
| "count": 3448211, | |
| "self": 177.17235782297212, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 5444.653615575167, | |
| "count": 6278904, | |
| "self": 5444.653615575167 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 14.878426522773225, | |
| "count": 3448211, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 31894.121644483617, | |
| "count": 3448211, | |
| "is_parallel": true, | |
| "self": 16656.71952841888, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0009833740186877549, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00021399903926067054, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0007693749794270843, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0007693749794270843 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.01157830300508067, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00039119800203479826, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00033826701110228896, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00033826701110228896 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.009729904995765537, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.009729904995765537 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0011189329961780459, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.00019885905203409493, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0009200739441439509, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0009200739441439509 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 15237.2309223208, | |
| "count": 3448210, | |
| "is_parallel": true, | |
| "self": 745.2196475994715, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 644.0528043218073, | |
| "count": 3448210, | |
| "is_parallel": true, | |
| "self": 644.0528043218073 | |
| }, | |
| "communicator.exchange": { | |
| "total": 11756.180057266814, | |
| "count": 3448210, | |
| "is_parallel": true, | |
| "self": 11756.180057266814 | |
| }, | |
| "steps_from_proto": { | |
| "total": 2091.778413132706, | |
| "count": 6896420, | |
| "is_parallel": true, | |
| "self": 341.26600825274363, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1750.5124048799626, | |
| "count": 27585680, | |
| "is_parallel": true, | |
| "self": 1750.5124048799626 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.17119374393951148, | |
| "count": 498, | |
| "is_parallel": true, | |
| "self": 0.029364814807195216, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.14182892913231626, | |
| "count": 1992, | |
| "is_parallel": true, | |
| "self": 0.14182892913231626 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 7904.883070606244, | |
| "count": 3448211, | |
| "self": 225.70775432881783, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 3317.168459789187, | |
| "count": 3448211, | |
| "self": 3307.642995674105, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 9.525464115082286, | |
| "count": 100, | |
| "self": 9.525464115082286 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 4362.006856488239, | |
| "count": 2424, | |
| "self": 2645.184580873087, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 1716.8222756151517, | |
| "count": 72726, | |
| "self": 1716.8222756151517 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 3.599852789193392e-07, | |
| "count": 1, | |
| "self": 3.599852789193392e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.09684089000802487, | |
| "count": 1, | |
| "self": 0.0014143690059427172, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.09542652100208215, | |
| "count": 1, | |
| "self": 0.09542652100208215 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |