{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9663176536560059, "min": 1.944616436958313, "max": 3.2956790924072266, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37375.765625, "min": 16802.291015625, "max": 140565.015625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.84415584415585, "min": 43.42342342342342, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19972.0, "min": 16548.0, "max": 23852.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1522.753577568688, "min": 1196.911204744865, "max": 1538.8142701663942, "count": 485 }, "SoccerTwos.Self-play.ELO.sum": { "value": 234504.05094557794, "min": 2394.2851093880768, "max": 338076.13474370027, "count": 485 }, "SoccerTwos.Step.mean": { "value": 4999995.0, "min": 9432.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999995.0, "min": 9432.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03327220305800438, "min": -0.1294293850660324, "max": 0.16844964027404785, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.157191276550293, "min": -21.485279083251953, "max": 29.310237884521484, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03264044597744942, "min": -0.11570771783590317, "max": 0.16762234270572662, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.059268951416016, "min": -19.207481384277344, "max": 29.16628646850586, "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": -0.03948000054205618, "min": -0.6467733323574066, "max": 0.36375000327825546, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.119400084018707, "min": -43.58000028133392, "max": 51.202799797058105, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03948000054205618, "min": -0.6467733323574066, "max": 0.36375000327825546, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.119400084018707, "min": -43.58000028133392, "max": 51.202799797058105, "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": 0.014715130932988056, "min": 0.008281694056434693, "max": 0.024242207625259957, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014715130932988056, "min": 0.008281694056434693, "max": 0.024242207625259957, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09423146148522694, "min": 7.307450359803625e-05, "max": 0.1153241919974486, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09423146148522694, "min": 7.307450359803625e-05, "max": 0.1153241919974486, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09703569759925207, "min": 7.508695762226125e-05, "max": 0.11773238157232603, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09703569759925207, "min": 7.508695762226125e-05, "max": 0.11773238157232603, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680076158", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "c:\\Users\\AllanSuzuki\\OneDrive - Metyis\\Documenten\\Projetos\\PPO_learning\\.conda\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.9.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1680098496" }, "total": 22346.8895283, "count": 1, "self": 3.658976699996856, "children": { "run_training.setup": { "total": 0.16504160000000034, "count": 1, "self": 0.16504160000000034 }, "TrainerController.start_learning": { "total": 22343.06551, "count": 1, "self": 11.287399000353616, "children": { "TrainerController._reset_env": { "total": 24.219085700004708, "count": 25, "self": 24.219085700004708 }, "TrainerController.advance": { "total": 22307.28623789964, "count": 338333, "self": 12.620085299102357, "children": { "env_step": { "total": 8135.860806299687, "count": 338333, "self": 6585.748427800044, "children": { "SubprocessEnvManager._take_step": { "total": 1542.9189981994111, "count": 338333, "self": 61.75467619935603, "children": { "TorchPolicy.evaluate": { "total": 1481.164322000055, "count": 633982, "self": 1481.164322000055 } } }, "workers": { "total": 7.193380300232221, "count": 338333, "self": 0.0, "children": { "worker_root": { "total": 22301.96793959938, "count": 338333, "is_parallel": true, "self": 16943.869986100042, "children": { "steps_from_proto": { "total": 0.07070160000675685, "count": 50, "is_parallel": true, "self": 0.014929700005126278, "children": { "_process_rank_one_or_two_observation": { "total": 0.05577190000163057, "count": 200, "is_parallel": true, "self": 0.05577190000163057 } } }, "UnityEnvironment.step": { "total": 5358.027251899332, "count": 338333, "is_parallel": true, "self": 259.2927229979732, "children": { "UnityEnvironment._generate_step_input": { "total": 208.32094120099777, "count": 338333, "is_parallel": true, "self": 208.32094120099777 }, "communicator.exchange": { "total": 4062.478123100001, "count": 338333, "is_parallel": true, "self": 4062.478123100001 }, "steps_from_proto": { "total": 827.9354646003608, "count": 676666, "is_parallel": true, "self": 162.50784180080507, "children": { "_process_rank_one_or_two_observation": { "total": 665.4276227995557, "count": 2706664, "is_parallel": true, "self": 665.4276227995557 } } } } } } } } } } }, "trainer_advance": { "total": 14158.805346300851, "count": 338333, "self": 77.29478620130612, "children": { "process_trajectory": { "total": 1763.1428840995713, "count": 338333, "self": 1760.3683818995723, "children": { "RLTrainer._checkpoint": { "total": 2.774502199999006, "count": 10, "self": 2.774502199999006 } } }, "_update_policy": { "total": 12318.367675999974, "count": 239, "self": 1214.6243261000127, "children": { "TorchPOCAOptimizer.update": { "total": 11103.743349899962, "count": 7170, "self": 11103.743349899962 } } } } } } }, "trainer_threads": { "total": 1.2999989849049598e-06, "count": 1, "self": 1.2999989849049598e-06 }, "TrainerController._save_models": { "total": 0.2727861000021221, "count": 1, "self": 0.01545290000285604, "children": { "RLTrainer._checkpoint": { "total": 0.25733319999926607, "count": 1, "self": 0.25733319999926607 } } } } } } }