{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.8629598617553711, "min": 0.8143925070762634, "max": 1.2603093385696411, "count": 1445 }, "SoccerTwos.Policy.Entropy.sum": { "value": 18004.794921875, "min": 14551.4384765625, "max": 31213.576171875, "count": 1445 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.24271844660194, "min": 37.446969696969695, "max": 71.7536231884058, "count": 1445 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19876.0, "min": 9664.0, "max": 21020.0, "count": 1445 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1612.3971518706778, "min": 1486.6617599398921, "max": 1650.5826978650584, "count": 1445 }, "SoccerTwos.Self-play.ELO.sum": { "value": 332153.81328535965, "min": 158409.12806094362, "max": 407722.2972394211, "count": 1445 }, "SoccerTwos.Step.mean": { "value": 49999916.0, "min": 35559964.0, "max": 49999916.0, "count": 1445 }, "SoccerTwos.Step.sum": { "value": 49999916.0, "min": 35559964.0, "max": 49999916.0, "count": 1445 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016623804345726967, "min": -0.15243105590343475, "max": 0.12159410119056702, "count": 1445 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.4078798294067383, "min": -28.047313690185547, "max": 22.738096237182617, "count": 1445 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.017473548650741577, "min": -0.14682802557945251, "max": 0.12256636470556259, "count": 1445 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.5820775032043457, "min": -27.016355514526367, "max": 22.919910430908203, "count": 1445 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1445 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1445 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.046679022254013436, "min": -0.3730349716593008, "max": 0.28139144500946617, "count": 1445 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.569199562072754, "min": -71.74399971961975, "max": 52.62020021677017, "count": 1445 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.046679022254013436, "min": -0.3730349716593008, "max": 0.28139144500946617, "count": 1445 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.569199562072754, "min": -71.74399971961975, "max": 52.62020021677017, "count": 1445 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1445 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1445 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017674256639353795, "min": 0.014022932092727085, "max": 0.02376349164454344, "count": 351 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017674256639353795, "min": 0.014022932092727085, "max": 0.02376349164454344, "count": 351 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11081945796807607, "min": 0.09687335416674614, "max": 0.1129289494206508, "count": 351 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11081945796807607, "min": 0.09687335416674614, "max": 0.1129289494206508, "count": 351 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11084932250281175, "min": 0.09165731941660245, "max": 0.11217189642290275, "count": 351 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11084932250281175, "min": 0.09165731941660245, "max": 0.11217189642290275, "count": 351 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.2274199257560318e-06, "min": 2.2274199257560318e-06, "max": 0.0008642338311922081, "count": 351 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.2274199257560318e-06, "min": 2.2274199257560318e-06, "max": 0.0008642338311922081, "count": 351 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.1001187904, "min": 0.1001187904, "max": 0.14609246720000008, "count": 351 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.1001187904, "min": 0.1001187904, "max": 0.14609246720000008, "count": 351 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.3704775600000055e-05, "min": 1.3704775600000055e-05, "max": 0.0014475088208, "count": 351 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.3704775600000055e-05, "min": 1.3704775600000055e-05, "max": 0.0014475088208, "count": 351 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676768873", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hecto\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=Thelma_&_Louise --no-graphics --num-envs=3 --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1676802300" }, "total": 33427.324150199995, "count": 1, "self": 0.8479972999994061, "children": { "run_training.setup": { "total": 0.2705250000000001, "count": 1, "self": 0.2705250000000001 }, "TrainerController.start_learning": { "total": 33426.205627899995, "count": 1, "self": 28.263657197625434, "children": { "TrainerController._reset_env": { "total": 6.037854100010124, "count": 59, "self": 6.037854100010124 }, "TrainerController.advance": { "total": 33391.76031590236, "count": 885358, "self": 28.28774980504386, "children": { "env_step": { "total": 6796.121398900717, "count": 885358, "self": 2477.345592801272, "children": { "SubprocessEnvManager._take_step": { "total": 4304.8944441997355, "count": 1019394, "self": 162.05538009983957, "children": { "TorchPolicy.evaluate": { "total": 4142.839064099896, "count": 1819034, "self": 4142.839064099896 } } }, "workers": { "total": 13.881361899709981, "count": 885358, "self": 0.0, "children": { "worker_root": { "total": 100222.2896411017, "count": 1019316, "is_parallel": true, "self": 89485.34619340113, "children": { "steps_from_proto": { "total": 0.29339250002142414, "count": 350, "is_parallel": true, "self": 0.05935049998653863, "children": { "_process_rank_one_or_two_observation": { "total": 0.2340420000348855, "count": 1400, "is_parallel": true, "self": 0.2340420000348855 } } }, "UnityEnvironment.step": { "total": 10736.65005520055, "count": 1019316, "is_parallel": true, "self": 588.1776321989819, "children": { "UnityEnvironment._generate_step_input": { "total": 447.3131549012912, "count": 1019316, "is_parallel": true, "self": 447.3131549012912 }, "communicator.exchange": { "total": 7933.19856660002, "count": 1019316, "is_parallel": true, "self": 7933.19856660002 }, "steps_from_proto": { "total": 1767.9607015002568, "count": 2038632, "is_parallel": true, "self": 370.9296551027139, "children": { "_process_rank_one_or_two_observation": { "total": 1397.031046397543, "count": 8154528, "is_parallel": true, "self": 1397.031046397543 } } } } } } } } } } }, "trainer_advance": { "total": 26567.351167196593, "count": 885358, "self": 208.2237521960742, "children": { "process_trajectory": { "total": 4900.549305000521, "count": 885358, "self": 4896.532178700524, "children": { "RLTrainer._checkpoint": { "total": 4.017126299996335, "count": 29, "self": 4.017126299996335 } } }, "_update_policy": { "total": 21458.57811, "count": 351, "self": 2261.212694700069, "children": { "TorchPOCAOptimizer.update": { "total": 19197.36541529993, "count": 21060, "self": 19197.36541529993 } } } } } } }, "trainer_threads": { "total": 1.1000010999850929e-06, "count": 1, "self": 1.1000010999850929e-06 }, "TrainerController._save_models": { "total": 0.14379960000223946, "count": 1, "self": 0.013834700002917089, "children": { "RLTrainer._checkpoint": { "total": 0.12996489999932237, "count": 1, "self": 0.12996489999932237 } } } } } } }