{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7659369707107544, "min": 1.7203421592712402, "max": 3.295672655105591, "count": 1090 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38031.21875, "min": 11739.75, "max": 130213.109375, "count": 1090 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.0, "min": 49.474747474747474, "max": 999.0, "count": 1090 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19968.0, "min": 16276.0, "max": 24224.0, "count": 1090 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1608.2078010282928, "min": 1188.8823242464416, "max": 1648.6443551710622, "count": 1002 }, "SoccerTwos.Self-play.ELO.sum": { "value": 250880.41696041368, "min": 2379.1972597319636, "max": 312370.98630354565, "count": 1002 }, "SoccerTwos.Step.mean": { "value": 10899960.0, "min": 9128.0, "max": 10899960.0, "count": 1090 }, "SoccerTwos.Step.sum": { "value": 10899960.0, "min": 9128.0, "max": 10899960.0, "count": 1090 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.003916190005838871, "min": -0.18354900181293488, "max": 0.17746126651763916, "count": 1090 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.6070094704627991, "min": -28.633644104003906, "max": 30.92393684387207, "count": 1090 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0045045362785458565, "min": -0.18280144035816193, "max": 0.17737747728824615, "count": 1090 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.6982031464576721, "min": -28.517024993896484, "max": 31.840614318847656, "count": 1090 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1090 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1090 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.13427483804764287, "min": -0.5943500027060509, "max": 0.5680352905217338, "count": 1090 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.812599897384644, "min": -82.98199987411499, "max": 75.61960005760193, "count": 1090 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.13427483804764287, "min": -0.5943500027060509, "max": 0.5680352905217338, "count": 1090 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.812599897384644, "min": -82.98199987411499, "max": 75.61960005760193, "count": 1090 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1090 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1090 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019092082366114482, "min": 0.00960920435754815, "max": 0.02530748783610761, "count": 521 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019092082366114482, "min": 0.00960920435754815, "max": 0.02530748783610761, "count": 521 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07850139290094375, "min": 1.9930038244334963e-06, "max": 0.1040394035478433, "count": 521 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07850139290094375, "min": 1.9930038244334963e-06, "max": 0.1040394035478433, "count": 521 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08014958600203197, "min": 2.294017387309092e-06, "max": 0.10686381285389264, "count": 521 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08014958600203197, "min": 2.294017387309092e-06, "max": 0.10686381285389264, "count": 521 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 521 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 521 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 521 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 521 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 521 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 521 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690664313", "python_version": "3.9.7 (default, Sep 16 2021, 23:53:23) \n[Clang 12.0.0 ]", "command_line_arguments": "/Users/undr/anaconda3/envs/unity-mla/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0.dev20230729", "numpy_version": "1.21.2", "end_time_seconds": "1690678037" }, "total": 13723.181449874999, "count": 1, "self": 0.05583404199933284, "children": { "run_training.setup": { "total": 0.013432875000000344, "count": 1, "self": 0.013432875000000344 }, "TrainerController.start_learning": { "total": 13723.112182958, "count": 1, "self": 5.781152442033999, "children": { "TrainerController._reset_env": { "total": 7.432005458998678, "count": 55, "self": 7.432005458998678 }, "TrainerController.advance": { "total": 13709.710535888968, "count": 730939, "self": 5.529195153605542, "children": { "env_step": { "total": 6268.882983924708, "count": 730939, "self": 5321.957614476973, "children": { "SubprocessEnvManager._take_step": { "total": 942.5259658713086, "count": 730939, "self": 29.93880636415554, "children": { "TorchPolicy.evaluate": { "total": 912.587159507153, "count": 1383068, "self": 912.587159507153 } } }, "workers": { "total": 4.399403576426698, "count": 730938, "self": 0.0, "children": { "worker_root": { "total": 13707.489054270187, "count": 730938, "is_parallel": true, "self": 9234.062994909022, "children": { "steps_from_proto": { "total": 0.04552682600947833, "count": 110, "is_parallel": true, "self": 0.008356047001264244, "children": { "_process_rank_one_or_two_observation": { "total": 0.03717077900821408, "count": 440, "is_parallel": true, "self": 0.03717077900821408 } } }, "UnityEnvironment.step": { "total": 4473.380532535155, "count": 730938, "is_parallel": true, "self": 236.4910693709444, "children": { "UnityEnvironment._generate_step_input": { "total": 112.99128580356553, "count": 730938, "is_parallel": true, "self": 112.99128580356553 }, "communicator.exchange": { "total": 3577.4010830494067, "count": 730938, "is_parallel": true, "self": 3577.4010830494067 }, "steps_from_proto": { "total": 546.4970943112389, "count": 1461876, "is_parallel": true, "self": 90.02199332977034, "children": { "_process_rank_one_or_two_observation": { "total": 456.4751009814686, "count": 5847504, "is_parallel": true, "self": 456.4751009814686 } } } } } } } } } } }, "trainer_advance": { "total": 7435.298356810655, "count": 730938, "self": 62.20059782378394, "children": { "process_trajectory": { "total": 1409.294024644861, "count": 730938, "self": 1405.5191973508631, "children": { "RLTrainer._checkpoint": { "total": 3.774827293997987, "count": 21, "self": 3.774827293997987 } } }, "_update_policy": { "total": 5963.80373434201, "count": 521, "self": 817.0109952249504, "children": { "TorchPOCAOptimizer.update": { "total": 5146.79273911706, "count": 15630, "self": 5146.79273911706 } } } } } } }, "trainer_threads": { "total": 4.5900014811195433e-07, "count": 1, "self": 4.5900014811195433e-07 }, "TrainerController._save_models": { "total": 0.18848870900001202, "count": 1, "self": 0.002269167000122252, "children": { "RLTrainer._checkpoint": { "total": 0.18621954199988977, "count": 1, "self": 0.18621954199988977 } } } } } } }