{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4511103630065918, "min": 1.424573540687561, "max": 3.295682668685913, "count": 1753 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26979.04296875, "min": 25946.181640625, "max": 105461.84375, "count": 1753 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 77.61904761904762, "min": 40.96638655462185, "max": 999.0, "count": 1753 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19560.0, "min": 8416.0, "max": 27620.0, "count": 1753 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1615.503282496499, "min": 1202.0326333979717, "max": 1710.7366365702744, "count": 1752 }, "SoccerTwos.Self-play.ELO.sum": { "value": 203553.41359455886, "min": 2405.3037547417584, "max": 389885.1082996513, "count": 1752 }, "SoccerTwos.Step.mean": { "value": 17529908.0, "min": 9828.0, "max": 17529908.0, "count": 1753 }, "SoccerTwos.Step.sum": { "value": 17529908.0, "min": 9828.0, "max": 17529908.0, "count": 1753 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0222158320248127, "min": -0.1273474246263504, "max": 0.16890715062618256, "count": 1753 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.799194812774658, "min": -19.033733367919922, "max": 29.889747619628906, "count": 1753 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02260405384004116, "min": -0.12866853177547455, "max": 0.16223177313804626, "count": 1753 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.8481106758117676, "min": -19.8258056640625, "max": 30.364227294921875, "count": 1753 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1753 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1753 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.024958727851746573, "min": -0.6928956508636475, "max": 0.5539918329034533, "count": 1753 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.1447997093200684, "min": -63.82279986143112, "max": 67.08880001306534, "count": 1753 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.024958727851746573, "min": -0.6928956508636475, "max": 0.5539918329034533, "count": 1753 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.1447997093200684, "min": -63.82279986143112, "max": 67.08880001306534, "count": 1753 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1753 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1753 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01969123772966365, "min": 0.011068875553125206, "max": 0.028425948153017088, "count": 849 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01969123772966365, "min": 0.011068875553125206, "max": 0.028425948153017088, "count": 849 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09342529103159905, "min": 0.001761433262921249, "max": 0.12119288568695387, "count": 849 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09342529103159905, "min": 0.001761433262921249, "max": 0.12119288568695387, "count": 849 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09476606398820878, "min": 0.001802619556353117, "max": 0.12373307670156161, "count": 849 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09476606398820878, "min": 0.001802619556353117, "max": 0.12373307670156161, "count": 849 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 849 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 849 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 849 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 849 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 849 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 849 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685785241", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/npg0/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=default --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": "1685928294" }, "total": 143052.9272272084, "count": 1, "self": 0.14630116522312164, "children": { "run_training.setup": { "total": 0.008112570270895958, "count": 1, "self": 0.008112570270895958 }, "TrainerController.start_learning": { "total": 143052.7728134729, "count": 1, "self": 28.223541285842657, "children": { "TrainerController._reset_env": { "total": 14.26833320222795, "count": 88, "self": 14.26833320222795 }, "TrainerController.advance": { "total": 143010.05111518688, "count": 1204662, "self": 27.31034628674388, "children": { "env_step": { "total": 137200.91371796094, "count": 1204662, "self": 133309.15305005945, "children": { "SubprocessEnvManager._take_step": { "total": 3875.4531029574573, "count": 1204662, "self": 140.04572109878063, "children": { "TorchPolicy.evaluate": { "total": 3735.4073818586767, "count": 2204072, "self": 3735.4073818586767 } } }, "workers": { "total": 16.307564944028854, "count": 1204661, "self": 0.0, "children": { "worker_root": { "total": 143001.97222033888, "count": 1204661, "is_parallel": true, "self": 12688.692400794476, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002761946991086006, "count": 2, "is_parallel": true, "self": 0.0005067139863967896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022552330046892166, "count": 8, "is_parallel": true, "self": 0.0022552330046892166 } } }, "UnityEnvironment.step": { "total": 0.13683645986020565, "count": 1, "is_parallel": true, "self": 0.00025064684450626373, "children": { "UnityEnvironment._generate_step_input": { "total": 0.004089776426553726, "count": 1, "is_parallel": true, "self": 0.004089776426553726 }, "communicator.exchange": { "total": 0.12985243648290634, "count": 1, "is_parallel": true, "self": 0.12985243648290634 }, "steps_from_proto": { "total": 0.002643600106239319, "count": 2, "is_parallel": true, "self": 0.0003811102360486984, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022624898701906204, "count": 8, "is_parallel": true, "self": 0.0022624898701906204 } } } } } } }, "UnityEnvironment.step": { "total": 130313.0622113347, "count": 1204660, "is_parallel": true, "self": 253.78334576450288, "children": { "UnityEnvironment._generate_step_input": { "total": 1559.9662080537528, "count": 1204660, "is_parallel": true, "self": 1559.9662080537528 }, "communicator.exchange": { "total": 125633.85390152968, "count": 1204660, "is_parallel": true, "self": 125633.85390152968 }, "steps_from_proto": { "total": 2865.458755986765, "count": 2409320, "is_parallel": true, "self": 410.41454009898007, "children": { "_process_rank_one_or_two_observation": { "total": 2455.044215887785, "count": 9637280, "is_parallel": true, "self": 2455.044215887785 } } } } }, "steps_from_proto": { "total": 0.21760820969939232, "count": 174, "is_parallel": true, "self": 0.031052814796566963, "children": { "_process_rank_one_or_two_observation": { "total": 0.18655539490282536, "count": 696, "is_parallel": true, "self": 0.18655539490282536 } } } } } } } } }, "trainer_advance": { "total": 5781.827050939202, "count": 1204661, "self": 204.53986318409443, "children": { "process_trajectory": { "total": 2175.4344605356455, "count": 1204661, "self": 2167.158844701946, "children": { "RLTrainer._checkpoint": { "total": 8.275615833699703, "count": 35, "self": 8.275615833699703 } } }, "_update_policy": { "total": 3401.8527272194624, "count": 849, "self": 2113.559172479436, "children": { "TorchPOCAOptimizer.update": { "total": 1288.2935547400266, "count": 25479, "self": 1288.2935547400266 } } } } } } }, "trainer_threads": { "total": 8.028000593185425e-07, "count": 1, "self": 8.028000593185425e-07 }, "TrainerController._save_models": { "total": 0.22982299514114857, "count": 1, "self": 0.0012078844010829926, "children": { "RLTrainer._checkpoint": { "total": 0.22861511074006557, "count": 1, "self": 0.22861511074006557 } } } } } } }