| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 3.142122745513916, | |
| "min": 2.8692078590393066, | |
| "max": 3.2957396507263184, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 50374.51171875, | |
| "min": 15793.908203125, | |
| "max": 134930.59375, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 834.5, | |
| "min": 441.45454545454544, | |
| "max": 999.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 20028.0, | |
| "min": 12564.0, | |
| "max": 28604.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1176.5429462814968, | |
| "min": 1175.069866654842, | |
| "max": 1205.5563253858497, | |
| "count": 288 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 2353.0858925629936, | |
| "min": 2350.139733309684, | |
| "max": 19252.745165865294, | |
| "count": 288 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 5419448.0, | |
| "min": 9320.0, | |
| "max": 5419448.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 5419448.0, | |
| "min": 9320.0, | |
| "max": 5419448.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.003984104376286268, | |
| "min": -0.02983948588371277, | |
| "max": 0.010335694998502731, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -0.04780925437808037, | |
| "min": -0.5371107459068298, | |
| "max": 0.18604251742362976, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0035634292289614677, | |
| "min": -0.027939442545175552, | |
| "max": 0.010346154682338238, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -0.04276115074753761, | |
| "min": -0.5029099583625793, | |
| "max": 0.18623077869415283, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.16666666666666666, | |
| "min": -0.5, | |
| "max": 0.3034000034843172, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -2.0, | |
| "min": -8.618399977684021, | |
| "max": 4.639999985694885, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.16666666666666666, | |
| "min": -0.5, | |
| "max": 0.3034000034843172, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -2.0, | |
| "min": -8.618399977684021, | |
| "max": 4.639999985694885, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 542 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.019610119580950897, | |
| "min": 0.011276822743335893, | |
| "max": 0.023445032841603583, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.019610119580950897, | |
| "min": 0.011276822743335893, | |
| "max": 0.023445032841603583, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.0021618504271221656, | |
| "min": 4.567420160602372e-08, | |
| "max": 0.007523580609510343, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.0021618504271221656, | |
| "min": 4.567420160602372e-08, | |
| "max": 0.007523580609510343, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.002163059695158154, | |
| "min": 4.019607852493816e-08, | |
| "max": 0.007522939518094063, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.002163059695158154, | |
| "min": 4.019607852493816e-08, | |
| "max": 0.007522939518094063, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 251 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 251 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1678532561", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/root/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", | |
| "mlagents_version": "0.31.0.dev0", | |
| "mlagents_envs_version": "0.31.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "1.11.0+cu102", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1678545460" | |
| }, | |
| "total": 12899.087798575987, | |
| "count": 1, | |
| "self": 0.13618274487089366, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.013107400038279593, | |
| "count": 1, | |
| "self": 0.013107400038279593 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 12898.938508431078, | |
| "count": 1, | |
| "self": 12.035885413875803, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 8.101249790750444, | |
| "count": 28, | |
| "self": 8.101249790750444 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 12878.456100711483, | |
| "count": 353694, | |
| "self": 12.117166964919306, | |
| "children": { | |
| "env_step": { | |
| "total": 10398.209307252895, | |
| "count": 353694, | |
| "self": 8073.051608109381, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 2317.3008903142763, | |
| "count": 353694, | |
| "self": 71.35492512304336, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 2245.945965191233, | |
| "count": 702380, | |
| "self": 2245.945965191233 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 7.856808829237707, | |
| "count": 353694, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 12876.49312289164, | |
| "count": 353694, | |
| "is_parallel": true, | |
| "self": 6233.237369406619, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.00334945204667747, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0008397098863497376, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0025097421603277326, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0025097421603277326 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.041864907019771636, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0013210601173341274, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00079390499740839, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00079390499740839 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.036261887988075614, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.036261887988075614 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.003488053916953504, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0007131376769393682, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.002774916240014136, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.002774916240014136 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 6643.188999443082, | |
| "count": 353693, | |
| "is_parallel": true, | |
| "self": 314.44781051948667, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 217.0314814611338, | |
| "count": 353693, | |
| "is_parallel": true, | |
| "self": 217.0314814611338 | |
| }, | |
| "communicator.exchange": { | |
| "total": 5199.109432811383, | |
| "count": 353693, | |
| "is_parallel": true, | |
| "self": 5199.109432811383 | |
| }, | |
| "steps_from_proto": { | |
| "total": 912.6002746510785, | |
| "count": 707386, | |
| "is_parallel": true, | |
| "self": 190.28183687792625, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 722.3184377731523, | |
| "count": 2829544, | |
| "is_parallel": true, | |
| "self": 722.3184377731523 | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.06675404193811119, | |
| "count": 54, | |
| "is_parallel": true, | |
| "self": 0.014197317534126341, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.052556724403984845, | |
| "count": 216, | |
| "is_parallel": true, | |
| "self": 0.052556724403984845 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 2468.129626493668, | |
| "count": 353694, | |
| "self": 96.21139795449562, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 640.7160151961725, | |
| "count": 353694, | |
| "self": 637.830245074234, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 2.885770121938549, | |
| "count": 10, | |
| "self": 2.885770121938549 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1731.202213343, | |
| "count": 252, | |
| "self": 1115.487153111375, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 615.7150602316251, | |
| "count": 7530, | |
| "self": 615.7150602316251 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.8819700926542282e-06, | |
| "count": 1, | |
| "self": 1.8819700926542282e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.34527063299901783, | |
| "count": 1, | |
| "self": 0.0030401740223169327, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.3422304589767009, | |
| "count": 1, | |
| "self": 0.3422304589767009 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |