{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2541470527648926, "min": 2.2264187335968018, "max": 3.2958130836486816, "count": 600 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44505.87890625, "min": 2003.854248046875, "max": 225908.15625, "count": 600 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.822916666666664, "min": 42.243478260869566, "max": 999.0, "count": 600 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19900.0, "min": 11988.0, "max": 32504.0, "count": 600 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1525.3226441654676, "min": 1199.384981924398, "max": 1541.9464998647475, "count": 586 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292861.9476797698, "min": 2398.769963848796, "max": 349523.70447069826, "count": 586 }, "SoccerTwos.Step.mean": { "value": 5999964.0, "min": 9476.0, "max": 5999964.0, "count": 600 }, "SoccerTwos.Step.sum": { "value": 5999964.0, "min": 9476.0, "max": 5999964.0, "count": 600 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006578030996024609, "min": -0.07075738161802292, "max": 0.14711181819438934, "count": 600 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.256403923034668, "min": -15.849653244018555, "max": 21.771282196044922, "count": 600 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00042870157631114125, "min": -0.08137570321559906, "max": 0.15133030712604523, "count": 600 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.08188199996948242, "min": -18.22815704345703, "max": 22.004295349121094, "count": 600 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 600 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 600 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08447329723398099, "min": -0.5101333335042, "max": 0.5614355537626479, "count": 600 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.13439977169037, "min": -39.12819993495941, "max": 55.46360003948212, "count": 600 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08447329723398099, "min": -0.5101333335042, "max": 0.5614355537626479, "count": 600 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.13439977169037, "min": -39.12819993495941, "max": 55.46360003948212, "count": 600 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 600 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 600 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0166406735116147, "min": 0.014553197751067476, "max": 0.02096656994221525, "count": 96 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0166406735116147, "min": 0.014553197751067476, "max": 0.02096656994221525, "count": 96 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09528738483786584, "min": 0.0014326320227054466, "max": 0.10267178962628047, "count": 96 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09528738483786584, "min": 0.0014326320227054466, "max": 0.10267178962628047, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10004813447594643, "min": 0.001436497309542675, "max": 0.10778420658575164, "count": 96 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10004813447594643, "min": 0.001436497309542675, "max": 0.10778420658575164, "count": 96 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 96 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 96 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 96 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999996, "min": 0.19999999999999996, "max": 0.19999999999999996, "count": 96 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 96 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.004999999999999999, "count": 96 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677412416", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/fbeghell/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --num-envs=3 --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos_v2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1677416509" }, "total": 4093.656747773988, "count": 1, "self": 0.2196339899674058, "children": { "run_training.setup": { "total": 0.021348519949242473, "count": 1, "self": 0.021348519949242473 }, "TrainerController.start_learning": { "total": 4093.4157652640715, "count": 1, "self": 7.478107919450849, "children": { "TrainerController._reset_env": { "total": 4.246652701403946, "count": 18, "self": 4.246652701403946 }, "TrainerController.advance": { "total": 4081.3988734942395, "count": 376605, "self": 7.324552450329065, "children": { "env_step": { "total": 2150.052749511553, "count": 376605, "self": 731.7759145805612, "children": { "SubprocessEnvManager._take_step": { "total": 1414.3715546100866, "count": 407059, "self": 43.13556841947138, "children": { "TorchPolicy.evaluate": { "total": 1371.2359861906152, "count": 769044, "self": 1371.2359861906152 } } }, "workers": { "total": 3.905280320905149, "count": 376605, "self": 0.0, "children": { "worker_root": { "total": 12267.75443618535, "count": 407036, "is_parallel": true, "self": 9066.076087541878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005463488167151809, "count": 6, "is_parallel": true, "self": 0.0015623001381754875, "children": { "_process_rank_one_or_two_observation": { "total": 0.0039011880289763212, "count": 24, "is_parallel": true, "self": 0.0039011880289763212 } } }, "UnityEnvironment.step": { "total": 0.053212333004921675, "count": 3, "is_parallel": true, "self": 0.001589423744007945, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010393550619482994, "count": 3, "is_parallel": true, "self": 0.0010393550619482994 }, "communicator.exchange": { "total": 0.045753989135846496, "count": 3, "is_parallel": true, "self": 0.045753989135846496 }, "steps_from_proto": { "total": 0.004829565063118935, "count": 6, "is_parallel": true, "self": 0.0010161756072193384, "children": { "_process_rank_one_or_two_observation": { "total": 0.003813389455899596, "count": 24, "is_parallel": true, "self": 0.003813389455899596 } } } } } } }, "UnityEnvironment.step": { "total": 3201.6111709214747, "count": 407033, "is_parallel": true, "self": 188.8647192621138, "children": { "UnityEnvironment._generate_step_input": { "total": 123.01010983204469, "count": 407033, "is_parallel": true, "self": 123.01010983204469 }, "communicator.exchange": { "total": 2299.7066926585976, "count": 407033, "is_parallel": true, "self": 2299.7066926585976 }, "steps_from_proto": { "total": 590.0296491687186, "count": 814066, "is_parallel": true, "self": 118.64347190852277, "children": { "_process_rank_one_or_two_observation": { "total": 471.38617726019584, "count": 3256264, "is_parallel": true, "self": 471.38617726019584 } } } } }, "steps_from_proto": { "total": 0.06717772199772298, "count": 102, "is_parallel": true, "self": 0.013331872411072254, "children": { "_process_rank_one_or_two_observation": { "total": 0.05384584958665073, "count": 408, "is_parallel": true, "self": 0.05384584958665073 } } } } } } } } }, "trainer_advance": { "total": 1924.0215715323575, "count": 376605, "self": 56.068650795845315, "children": { "process_trajectory": { "total": 612.8880028438289, "count": 376605, "self": 609.3015440409072, "children": { "RLTrainer._checkpoint": { "total": 3.5864588029216975, "count": 12, "self": 3.5864588029216975 } } }, "_update_policy": { "total": 1255.0649178926833, "count": 96, "self": 667.3783815919887, "children": { "TorchPOCAOptimizer.update": { "total": 587.6865363006946, "count": 8640, "self": 587.6865363006946 } } } } } } }, "trainer_threads": { "total": 5.818437784910202e-07, "count": 1, "self": 5.818437784910202e-07 }, "TrainerController._save_models": { "total": 0.29213056713342667, "count": 1, "self": 0.0031741161365062, "children": { "RLTrainer._checkpoint": { "total": 0.28895645099692047, "count": 1, "self": 0.28895645099692047 } } } } } } }