| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.814974308013916, | |
| "min": 1.7633943557739258, | |
| "max": 3.29575252532959, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 36589.8828125, | |
| "min": 13200.7138671875, | |
| "max": 114470.890625, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 45.407407407407405, | |
| "min": 35.6865671641791, | |
| "max": 999.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19616.0, | |
| "min": 11588.0, | |
| "max": 30096.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1491.125756455233, | |
| "min": 1201.2421091626256, | |
| "max": 1505.2723340072453, | |
| "count": 491 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 322083.1633943303, | |
| "min": 2403.301746740039, | |
| "max": 396736.09886158083, | |
| "count": 491 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 4999848.0, | |
| "min": 9066.0, | |
| "max": 4999848.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 4999848.0, | |
| "min": 9066.0, | |
| "max": 4999848.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.045013878494501114, | |
| "min": -0.13065846264362335, | |
| "max": 0.15592828392982483, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -9.722997665405273, | |
| "min": -27.96091079711914, | |
| "max": 38.202430725097656, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.046934738755226135, | |
| "min": -0.1341095268726349, | |
| "max": 0.15659089386463165, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -10.137903213500977, | |
| "min": -28.699440002441406, | |
| "max": 37.71289825439453, | |
| "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": -0.039942592934325886, | |
| "min": -0.5856400012969971, | |
| "max": 0.5111698630737932, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -8.627600073814392, | |
| "min": -82.45099991559982, | |
| "max": 56.61560016870499, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.039942592934325886, | |
| "min": -0.5856400012969971, | |
| "max": 0.5111698630737932, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -8.627600073814392, | |
| "min": -82.45099991559982, | |
| "max": 56.61560016870499, | |
| "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": 0.012566837597599563, | |
| "min": 0.010382519401415873, | |
| "max": 0.025903802906395868, | |
| "count": 240 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.012566837597599563, | |
| "min": 0.010382519401415873, | |
| "max": 0.025903802906395868, | |
| "count": 240 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.12692004963755607, | |
| "min": 7.000466393947136e-05, | |
| "max": 0.13487323969602585, | |
| "count": 240 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.12692004963755607, | |
| "min": 7.000466393947136e-05, | |
| "max": 0.13487323969602585, | |
| "count": 240 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.12931963553031287, | |
| "min": 7.382410900997153e-05, | |
| "max": 0.13686487426360447, | |
| "count": 240 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.12931963553031287, | |
| "min": 7.382410900997153e-05, | |
| "max": 0.13686487426360447, | |
| "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": "1678764878", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "C:\\Notes\\drl-course\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "1.13.1+cpu", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1678796603" | |
| }, | |
| "total": 31724.854561800003, | |
| "count": 1, | |
| "self": 0.544815600002039, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.22925430000000002, | |
| "count": 1, | |
| "self": 0.22925430000000002 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 31724.0804919, | |
| "count": 1, | |
| "self": 15.183050999705301, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 5.926682000001983, | |
| "count": 25, | |
| "self": 5.926682000001983 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 31702.719917500297, | |
| "count": 345516, | |
| "self": 16.836411301741464, | |
| "children": { | |
| "env_step": { | |
| "total": 12136.688460399371, | |
| "count": 345516, | |
| "self": 9618.453549300712, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 2508.205003499238, | |
| "count": 345516, | |
| "self": 96.13952259947018, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 2412.065480899768, | |
| "count": 629718, | |
| "self": 2412.065480899768 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 10.029907599421822, | |
| "count": 345516, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 31694.525312700403, | |
| "count": 345516, | |
| "is_parallel": true, | |
| "self": 23925.199966901106, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.09313079999566298, | |
| "count": 50, | |
| "is_parallel": true, | |
| "self": 0.020926200016525343, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.07220459997913764, | |
| "count": 200, | |
| "is_parallel": true, | |
| "self": 0.07220459997913764 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 7769.232214999303, | |
| "count": 345516, | |
| "is_parallel": true, | |
| "self": 438.3739221002161, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 384.2993512994746, | |
| "count": 345516, | |
| "is_parallel": true, | |
| "self": 384.2993512994746 | |
| }, | |
| "communicator.exchange": { | |
| "total": 5461.771801900997, | |
| "count": 345516, | |
| "is_parallel": true, | |
| "self": 5461.771801900997 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1484.7871396986156, | |
| "count": 691032, | |
| "is_parallel": true, | |
| "self": 290.16315419870944, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1194.6239854999062, | |
| "count": 2764128, | |
| "is_parallel": true, | |
| "self": 1194.6239854999062 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 19549.195045799184, | |
| "count": 345516, | |
| "self": 92.11313789905034, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 3098.2860601001325, | |
| "count": 345516, | |
| "self": 3095.9418652001336, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 2.344194899998911, | |
| "count": 10, | |
| "self": 2.344194899998911 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 16358.795847800002, | |
| "count": 240, | |
| "self": 1257.692684700005, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 15101.103163099997, | |
| "count": 7200, | |
| "self": 15101.103163099997 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.7999991541728377e-06, | |
| "count": 1, | |
| "self": 1.7999991541728377e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.2508395999975619, | |
| "count": 1, | |
| "self": 0.016176199995243223, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.23466340000231867, | |
| "count": 1, | |
| "self": 0.23466340000231867 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |