| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.9531906843185425, | |
| "min": 1.9333367347717285, | |
| "max": 3.2957451343536377, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 42313.921875, | |
| "min": 20685.5234375, | |
| "max": 110978.8046875, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 57.89411764705882, | |
| "min": 45.570093457943926, | |
| "max": 999.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19684.0, | |
| "min": 9304.0, | |
| "max": 31968.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 4999918.0, | |
| "min": 9000.0, | |
| "max": 4999918.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 4999918.0, | |
| "min": 9000.0, | |
| "max": 4999918.0, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.06822053343057632, | |
| "min": -0.13340337574481964, | |
| "max": 0.17353291809558868, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 11.597490310668945, | |
| "min": -22.678573608398438, | |
| "max": 27.418201446533203, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.06983315944671631, | |
| "min": -0.12757983803749084, | |
| "max": 0.16391581296920776, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 11.871637344360352, | |
| "min": -21.68857192993164, | |
| "max": 25.898698806762695, | |
| "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": 0.09850823598749497, | |
| "min": -0.5384615384615384, | |
| "max": 0.487155556678772, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": 16.746400117874146, | |
| "min": -65.81360006332397, | |
| "max": 48.89580023288727, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": 0.09850823598749497, | |
| "min": -0.5384615384615384, | |
| "max": 0.487155556678772, | |
| "count": 500 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": 16.746400117874146, | |
| "min": -65.81360006332397, | |
| "max": 48.89580023288727, | |
| "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.Self-play.ELO.mean": { | |
| "value": 1516.2468810022674, | |
| "min": 1192.28374816736, | |
| "max": 1522.8103071340324, | |
| "count": 414 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 257761.96977038548, | |
| "min": 2385.845780844732, | |
| "max": 310656.77838486026, | |
| "count": 414 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.014279249346388193, | |
| "min": 0.01140843817035299, | |
| "max": 0.025414117853021403, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.014279249346388193, | |
| "min": 0.01140843817035299, | |
| "max": 0.025414117853021403, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.08459945817788442, | |
| "min": 3.708402582939622e-07, | |
| "max": 0.1083966962993145, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.08459945817788442, | |
| "min": 3.708402582939622e-07, | |
| "max": 0.1083966962993145, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.0862138512233893, | |
| "min": 5.9369759431623e-07, | |
| "max": 0.11099762643376986, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.0862138512233893, | |
| "min": 5.9369759431623e-07, | |
| "max": 0.11099762643376986, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 237 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 237 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1675613821", | |
| "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", | |
| "command_line_arguments": "C:\\Users\\Francisco\\anaconda3\\envs\\rl\\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": "1.13.1+cpu", | |
| "numpy_version": "1.21.2", | |
| "end_time_seconds": "1675632219" | |
| }, | |
| "total": 18398.338030699997, | |
| "count": 1, | |
| "self": 0.44735779999609804, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.12766220000000006, | |
| "count": 1, | |
| "self": 0.12766220000000006 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 18397.7630107, | |
| "count": 1, | |
| "self": 10.556686000109039, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 6.009154099999812, | |
| "count": 25, | |
| "self": 6.009154099999812 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 18381.032313799893, | |
| "count": 336211, | |
| "self": 10.097430798919959, | |
| "children": { | |
| "env_step": { | |
| "total": 7878.255441100767, | |
| "count": 336211, | |
| "self": 6209.0573362012565, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 1662.1884631005626, | |
| "count": 336211, | |
| "self": 60.01698679983224, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 1602.1714763007303, | |
| "count": 635166, | |
| "self": 1602.1714763007303 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 7.009641798948309, | |
| "count": 336211, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 18377.433205799953, | |
| "count": 336211, | |
| "is_parallel": true, | |
| "self": 13398.232135199562, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.05499650000088252, | |
| "count": 50, | |
| "is_parallel": true, | |
| "self": 0.012067300012920334, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.042929199987962186, | |
| "count": 200, | |
| "is_parallel": true, | |
| "self": 0.042929199987962186 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 4979.14607410039, | |
| "count": 336211, | |
| "is_parallel": true, | |
| "self": 240.76061850083715, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 205.50819700051986, | |
| "count": 336211, | |
| "is_parallel": true, | |
| "self": 205.50819700051986 | |
| }, | |
| "communicator.exchange": { | |
| "total": 3728.012818700003, | |
| "count": 336211, | |
| "is_parallel": true, | |
| "self": 3728.012818700003 | |
| }, | |
| "steps_from_proto": { | |
| "total": 804.86443989903, | |
| "count": 672422, | |
| "is_parallel": true, | |
| "self": 168.9518741989816, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 635.9125657000484, | |
| "count": 2689688, | |
| "is_parallel": true, | |
| "self": 635.9125657000484 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 10492.679441900207, | |
| "count": 336211, | |
| "self": 76.79321610071383, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 1569.9522774994998, | |
| "count": 336211, | |
| "self": 1568.0727003995046, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.879577099995231, | |
| "count": 10, | |
| "self": 1.879577099995231 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 8845.933948299993, | |
| "count": 237, | |
| "self": 920.2543032999702, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 7925.679645000023, | |
| "count": 7110, | |
| "self": 7925.679645000023 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.6999983927235007e-06, | |
| "count": 1, | |
| "self": 1.6999983927235007e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.1648550999998406, | |
| "count": 1, | |
| "self": 0.0038491999985126313, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.16100590000132797, | |
| "count": 1, | |
| "self": 0.16100590000132797 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |