{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9380950927734375, "min": 1.884420394897461, "max": 3.295722723007202, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38079.69140625, "min": 12560.1220703125, "max": 122356.4375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.0, "min": 36.96969696969697, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19584.0, "min": 11224.0, "max": 30616.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1561.2096121658135, "min": 1195.5250248073567, "max": 1576.2787634900967, "count": 496 }, "SoccerTwos.Self-play.ELO.sum": { "value": 318486.76088182593, "min": 2395.8409891228844, "max": 398085.303234156, "count": 496 }, "SoccerTwos.Step.mean": { "value": 4999994.0, "min": 9324.0, "max": 4999994.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999994.0, "min": 9324.0, "max": 4999994.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.052598390728235245, "min": -0.1395639181137085, "max": 0.15337607264518738, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.677473068237305, "min": -22.85717010498047, "max": 30.52715301513672, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04873089864850044, "min": -0.14018721878528595, "max": 0.15499074757099152, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 9.892372131347656, "min": -24.000629425048828, "max": 29.49363136291504, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.14276847228628073, "min": -0.6666666666666666, "max": 0.5693066676457723, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 28.98199987411499, "min": -55.05440014600754, "max": 65.42999994754791, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.14276847228628073, "min": -0.6666666666666666, "max": 0.5693066676457723, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 28.98199987411499, "min": -55.05440014600754, "max": 65.42999994754791, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016979035355810388, "min": 0.011221990780662357, "max": 0.02364096590705837, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016979035355810388, "min": 0.011221990780662357, "max": 0.02364096590705837, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11154008607069651, "min": 0.00013263700105502115, "max": 0.12990815689166388, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11154008607069651, "min": 0.00013263700105502115, "max": 0.12990815689166388, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11382811665534973, "min": 0.00013184775089030153, "max": 0.1324552245438099, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11382811665534973, "min": 0.00013184775089030153, "max": 0.1324552245438099, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698889575", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/alessio/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1698900283" }, "total": 10708.268390117999, "count": 1, "self": 0.2719648979982594, "children": { "run_training.setup": { "total": 0.007502995998947881, "count": 1, "self": 0.007502995998947881 }, "TrainerController.start_learning": { "total": 10707.988922224002, "count": 1, "self": 7.132997272870853, "children": { "TrainerController._reset_env": { "total": 1.7016249989828793, "count": 25, "self": 1.7016249989828793 }, "TrainerController.advance": { "total": 10699.03658405815, "count": 342831, "self": 7.247330288490048, "children": { "env_step": { "total": 5806.975383968893, "count": 342831, "self": 4811.102445408891, "children": { "SubprocessEnvManager._take_step": { "total": 990.6575932021951, "count": 342831, "self": 35.35666112994659, "children": { "TorchPolicy.evaluate": { "total": 955.3009320722485, "count": 632018, "self": 955.3009320722485 } } }, "workers": { "total": 5.215345357806655, "count": 342831, "self": 0.0, "children": { "worker_root": { "total": 10696.103393612895, "count": 342831, "is_parallel": true, "self": 6696.867310496047, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014362229994731024, "count": 2, "is_parallel": true, "self": 0.00034484000934753567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010913829901255667, "count": 8, "is_parallel": true, "self": 0.0010913829901255667 } } }, "UnityEnvironment.step": { "total": 0.022645452991127968, "count": 1, "is_parallel": true, "self": 0.00038507996941916645, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006521750037791207, "count": 1, "is_parallel": true, "self": 0.0006521750037791207 }, "communicator.exchange": { "total": 0.020543377002468333, "count": 1, "is_parallel": true, "self": 0.020543377002468333 }, "steps_from_proto": { "total": 0.001064821015461348, "count": 2, "is_parallel": true, "self": 0.00023214200336951762, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008326790120918304, "count": 8, "is_parallel": true, "self": 0.0008326790120918304 } } } } } } }, "UnityEnvironment.step": { "total": 3999.197964198771, "count": 342830, "is_parallel": true, "self": 238.07523548669997, "children": { "UnityEnvironment._generate_step_input": { "total": 182.4201008824166, "count": 342830, "is_parallel": true, "self": 182.4201008824166 }, "communicator.exchange": { "total": 2947.4947717185423, "count": 342830, "is_parallel": true, "self": 2947.4947717185423 }, "steps_from_proto": { "total": 631.207856111112, "count": 685660, "is_parallel": true, "self": 112.40725167475466, "children": { "_process_rank_one_or_two_observation": { "total": 518.8006044363574, "count": 2742640, "is_parallel": true, "self": 518.8006044363574 } } } } }, "steps_from_proto": { "total": 0.03811891807708889, "count": 48, "is_parallel": true, "self": 0.007000403085839935, "children": { "_process_rank_one_or_two_observation": { "total": 0.031118514991248958, "count": 192, "is_parallel": true, "self": 0.031118514991248958 } } } } } } } } }, "trainer_advance": { "total": 4884.813869800768, "count": 342831, "self": 60.30110088577203, "children": { "process_trajectory": { "total": 947.3283799269702, "count": 342831, "self": 946.2569854929752, "children": { "RLTrainer._checkpoint": { "total": 1.0713944339950103, "count": 10, "self": 1.0713944339950103 } } }, "_update_policy": { "total": 3877.1843889880256, "count": 240, "self": 513.6047575530101, "children": { "TorchPOCAOptimizer.update": { "total": 3363.5796314350155, "count": 7200, "self": 3363.5796314350155 } } } } } } }, "trainer_threads": { "total": 7.719936547800899e-07, "count": 1, "self": 7.719936547800899e-07 }, "TrainerController._save_models": { "total": 0.11771512200357392, "count": 1, "self": 0.001220716003444977, "children": { "RLTrainer._checkpoint": { "total": 0.11649440600012895, "count": 1, "self": 0.11649440600012895 } } } } } } }