{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9775105714797974, "min": 1.9029415845870972, "max": 3.2104265689849854, "count": 451 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38727.56640625, "min": 21382.5, "max": 123387.5, "count": 451 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.88636363636363, "min": 37.42307692307692, "max": 999.0, "count": 451 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19320.0, "min": 1104.0, "max": 23092.0, "count": 451 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1505.3681341327551, "min": 1203.4271524292199, "max": 1540.071787454504, "count": 447 }, "SoccerTwos.Self-play.ELO.sum": { "value": 264944.7916073649, "min": 2407.3486368510767, "max": 369398.3312739985, "count": 447 }, "SoccerTwos.Step.mean": { "value": 4999990.0, "min": 499995.0, "max": 4999990.0, "count": 451 }, "SoccerTwos.Step.sum": { "value": 4999990.0, "min": 499995.0, "max": 4999990.0, "count": 451 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.030934393405914307, "min": -0.11619401723146439, "max": 0.1773293912410736, "count": 451 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.444453239440918, "min": -21.37969970703125, "max": 25.8845272064209, "count": 451 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03077394887804985, "min": -0.11339270323514938, "max": 0.17394278943538666, "count": 451 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.416214942932129, "min": -20.8642578125, "max": 25.584335327148438, "count": 451 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 451 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 451 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11590227281505411, "min": -0.49979999886923715, "max": 0.4204000094357659, "count": 451 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.398800015449524, "min": -66.13480019569397, "max": 64.18079996109009, "count": 451 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11590227281505411, "min": -0.49979999886923715, "max": 0.4204000094357659, "count": 451 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.398800015449524, "min": -66.13480019569397, "max": 64.18079996109009, "count": 451 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 451 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 451 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016064612804135927, "min": 0.011230932494315008, "max": 0.023326970932733577, "count": 217 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016064612804135927, "min": 0.011230932494315008, "max": 0.023326970932733577, "count": 217 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10173258284727732, "min": 9.358472416352016e-05, "max": 0.11536166667938233, "count": 217 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10173258284727732, "min": 9.358472416352016e-05, "max": 0.11536166667938233, "count": 217 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10323344394564629, "min": 9.461922381888143e-05, "max": 0.1185214377939701, "count": 217 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10323344394564629, "min": 9.461922381888143e-05, "max": 0.1185214377939701, "count": 217 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 217 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 217 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 217 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 217 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 217 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 217 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692317844", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Suhas\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.22.3", "end_time_seconds": "1692332984" }, "total": 15139.9569658, "count": 1, "self": 0.343457999999373, "children": { "run_training.setup": { "total": 0.1411720999999999, "count": 1, "self": 0.1411720999999999 }, "TrainerController.start_learning": { "total": 15139.4723357, "count": 1, "self": 9.163248499909969, "children": { "TrainerController._reset_env": { "total": 5.250230599997067, "count": 24, "self": 5.250230599997067 }, "TrainerController.advance": { "total": 15124.872202800094, "count": 309558, "self": 9.749766600098155, "children": { "env_step": { "total": 6678.821595899721, "count": 309558, "self": 5324.054695700466, "children": { "SubprocessEnvManager._take_step": { "total": 1349.2055532993356, "count": 309558, "self": 48.522392599005116, "children": { "TorchPolicy.evaluate": { "total": 1300.6831607003305, "count": 566528, "self": 1300.6831607003305 } } }, "workers": { "total": 5.56134689991896, "count": 309558, "self": 0.0, "children": { "worker_root": { "total": 15121.914897800003, "count": 309558, "is_parallel": true, "self": 10805.57860709999, "children": { "steps_from_proto": { "total": 0.04813859999920567, "count": 48, "is_parallel": true, "self": 0.010202999990520212, "children": { "_process_rank_one_or_two_observation": { "total": 0.037935600008685455, "count": 192, "is_parallel": true, "self": 0.037935600008685455 } } }, "UnityEnvironment.step": { "total": 4316.288152100014, "count": 309558, "is_parallel": true, "self": 202.2668226000269, "children": { "UnityEnvironment._generate_step_input": { "total": 168.70445990029634, "count": 309558, "is_parallel": true, "self": 168.70445990029634 }, "communicator.exchange": { "total": 3279.309305799878, "count": 309558, "is_parallel": true, "self": 3279.309305799878 }, "steps_from_proto": { "total": 666.0075637998121, "count": 619116, "is_parallel": true, "self": 136.77321300118388, "children": { "_process_rank_one_or_two_observation": { "total": 529.2343507986283, "count": 2476464, "is_parallel": true, "self": 529.2343507986283 } } } } } } } } } } }, "trainer_advance": { "total": 8436.300840300275, "count": 309558, "self": 63.664593800151124, "children": { "process_trajectory": { "total": 1507.2387323001317, "count": 309558, "self": 1505.335484300132, "children": { "RLTrainer._checkpoint": { "total": 1.9032479999995076, "count": 10, "self": 1.9032479999995076 } } }, "_update_policy": { "total": 6865.397514199993, "count": 217, "self": 790.9903271999165, "children": { "TorchPOCAOptimizer.update": { "total": 6074.407187000076, "count": 6510, "self": 6074.407187000076 } } } } } } }, "trainer_threads": { "total": 8.000006346264854e-07, "count": 1, "self": 8.000006346264854e-07 }, "TrainerController._save_models": { "total": 0.18665299999884155, "count": 1, "self": 0.010772999998152955, "children": { "RLTrainer._checkpoint": { "total": 0.1758800000006886, "count": 1, "self": 0.1758800000006886 } } } } } } }