| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.4048619270324707, | |
| "min": 1.3750499486923218, | |
| "max": 1.7051565647125244, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 28277.060546875, | |
| "min": 14701.9814453125, | |
| "max": 34322.671875, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 45.06422018348624, | |
| "min": 35.125, | |
| "max": 53.40425531914894, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19648.0, | |
| "min": 8072.0, | |
| "max": 20960.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1607.9046472284606, | |
| "min": 1555.6832652825399, | |
| "max": 1613.038356436412, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 350523.2130958044, | |
| "min": 163654.2453609866, | |
| "max": 434134.2547516843, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 9999982.0, | |
| "min": 6659988.0, | |
| "max": 9999982.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 9999982.0, | |
| "min": 6659988.0, | |
| "max": 9999982.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.03223046660423279, | |
| "min": -0.11106479167938232, | |
| "max": 0.10332842171192169, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 13.246722221374512, | |
| "min": -46.31401824951172, | |
| "max": 44.017906188964844, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.031953852623701096, | |
| "min": -0.11250180751085281, | |
| "max": 0.10477326810359955, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 13.133033752441406, | |
| "min": -46.91325378417969, | |
| "max": 44.6334114074707, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": 0.09531192604554903, | |
| "min": -0.381275439994377, | |
| "max": 0.26663347656634745, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 20.777999877929688, | |
| "min": -86.93080031871796, | |
| "max": 62.125600039958954, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.09531192604554903, | |
| "min": -0.381275439994377, | |
| "max": 0.26663347656634745, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 20.777999877929688, | |
| "min": -86.93080031871796, | |
| "max": 62.125600039958954, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 335 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.01046212162455049, | |
| "min": 0.009879295097471185, | |
| "max": 0.014559235423075734, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.01046212162455049, | |
| "min": 0.009879295097471185, | |
| "max": 0.014559235423075734, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.05891079842112958, | |
| "min": 0.04971672408282757, | |
| "max": 0.05918900854885578, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.05891079842112958, | |
| "min": 0.04971672408282757, | |
| "max": 0.05918900854885578, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.05924153439700604, | |
| "min": 0.051102403877303006, | |
| "max": 0.05954511137679219, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.05924153439700604, | |
| "min": 0.051102403877303006, | |
| "max": 0.05954511137679219, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 6.4449295954992225e-09, | |
| "min": 6.4449295954992225e-09, | |
| "max": 0.00014248644558948728, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 6.4449295954992225e-09, | |
| "min": 6.4449295954992225e-09, | |
| "max": 0.00014248644558948728, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.10000085146159124, | |
| "min": 0.10000085146159124, | |
| "max": 0.11912103967704953, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.10000085146159124, | |
| "min": 0.10000085146159124, | |
| "max": 0.11912103967704953, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 1.0002659404254946e-05, | |
| "min": 1.0002659404254946e-05, | |
| "max": 6.972151274949521e-05, | |
| "count": 51 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 1.0002659404254946e-05, | |
| "min": 1.0002659404254946e-05, | |
| "max": 6.972151274949521e-05, | |
| "count": 51 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1710343829", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/home/stephan/.conda/envs/rl/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-read-deal --width=1280 --height=720 --resume", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.1+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1710353568" | |
| }, | |
| "total": 9739.254863360999, | |
| "count": 1, | |
| "self": 0.270132729987381, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.018506341002648696, | |
| "count": 1, | |
| "self": 0.018506341002648696 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 9738.966224290009, | |
| "count": 1, | |
| "self": 4.652608350283117, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.244304390012985, | |
| "count": 7, | |
| "self": 4.244304390012985 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 9729.947026144713, | |
| "count": 239073, | |
| "self": 4.148107524248189, | |
| "children": { | |
| "env_step": { | |
| "total": 4354.3673745146225, | |
| "count": 239073, | |
| "self": 3721.0493522615725, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 630.4299217515072, | |
| "count": 239073, | |
| "self": 19.02124206413282, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 611.4086796873744, | |
| "count": 418182, | |
| "self": 611.4086796873744 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.8881005015427945, | |
| "count": 239073, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 9731.739510110943, | |
| "count": 239073, | |
| "is_parallel": true, | |
| "self": 6533.360267171403, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.06389564499841072, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.000593470991589129, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.06330217400682159, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.06330217400682159 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.02612613000383135, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000600070008658804, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00040655999328009784, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00040655999328009784 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.02343449799809605, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.02343449799809605 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016850020037963986, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0003057300054933876, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001379271998303011, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001379271998303011 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.012151043978519738, | |
| "count": 12, | |
| "is_parallel": true, | |
| "self": 0.002059131977148354, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.010091912001371384, | |
| "count": 48, | |
| "is_parallel": true, | |
| "self": 0.010091912001371384 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 3198.3670918955613, | |
| "count": 239072, | |
| "is_parallel": true, | |
| "self": 175.16570653802773, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 110.43290661888022, | |
| "count": 239072, | |
| "is_parallel": true, | |
| "self": 110.43290661888022 | |
| }, | |
| "communicator.exchange": { | |
| "total": 2470.8126502879313, | |
| "count": 239072, | |
| "is_parallel": true, | |
| "self": 2470.8126502879313 | |
| }, | |
| "steps_from_proto": { | |
| "total": 441.95582845072204, | |
| "count": 478144, | |
| "is_parallel": true, | |
| "self": 78.3687699053844, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 363.58705854533764, | |
| "count": 1912576, | |
| "is_parallel": true, | |
| "self": 363.58705854533764 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 5371.4315441058425, | |
| "count": 239073, | |
| "self": 26.83088273082103, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 1094.2377518599678, | |
| "count": 239073, | |
| "self": 1093.3974272879568, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.8403245720110135, | |
| "count": 7, | |
| "self": 0.8403245720110135 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 4250.362909515054, | |
| "count": 51, | |
| "self": 652.032682771809, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 3598.3302267432446, | |
| "count": 4080, | |
| "self": 3598.3302267432446 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 9.200011845678091e-07, | |
| "count": 1, | |
| "self": 9.200011845678091e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.12228448499809019, | |
| "count": 1, | |
| "self": 0.0026952329935738817, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.11958925200451631, | |
| "count": 1, | |
| "self": 0.11958925200451631 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |