{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4303474426269531, "min": 1.1953974962234497, "max": 3.29569411277771, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 19132.328125, "min": 16187.94921875, "max": 143469.59375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 283.05263157894734, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 16156.0, "max": 23956.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.4411450126954, "min": 1189.2658214645403, "max": 1221.1020871596347, "count": 348 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2408.882290025391, "min": 2378.5316429290806, "max": 38542.76393313485, "count": 348 }, "SoccerTwos.Step.mean": { "value": 49999574.0, "min": 9232.0, "max": 49999574.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999574.0, "min": 9232.0, "max": 49999574.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 8.863906987244263e-05, "min": -0.09684797376394272, "max": 0.039017047733068466, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0008863906841725111, "min": -1.4526851177215576, "max": 0.39017048478126526, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 8.832582534523681e-05, "min": -0.09686007350683212, "max": 0.03836328908801079, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0008832582389004529, "min": -1.4529011249542236, "max": 0.3836328983306885, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6857384592294693, "max": 0.30922666390736897, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -17.829199939966202, "max": 7.01119989156723, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6857384592294693, "max": 0.30922666390736897, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -17.829199939966202, "max": 7.01119989156723, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019303698907606304, "min": 0.009621734620789841, "max": 0.025912615560810082, "count": 2287 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019303698907606304, "min": 0.009621734620789841, "max": 0.025912615560810082, "count": 2287 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.3651335052193106e-07, "min": 7.843297929535642e-12, "max": 0.017249827086925507, "count": 2287 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.3651335052193106e-07, "min": 7.843297929535642e-12, "max": 0.017249827086925507, "count": 2287 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.364581883098644e-07, "min": 1.3570412126194068e-11, "max": 0.01751269195228815, "count": 2287 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.364581883098644e-07, "min": 1.3570412126194068e-11, "max": 0.01751269195228815, "count": 2287 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2287 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2287 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2287 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2287 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2287 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2287 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709392019", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709509854" }, "total": 117835.85971496999, "count": 1, "self": 0.4010079428553581, "children": { "run_training.setup": { "total": 0.04044067859649658, "count": 1, "self": 0.04044067859649658 }, "TrainerController.start_learning": { "total": 117835.41826634854, "count": 1, "self": 49.42197136580944, "children": { "TrainerController._reset_env": { "total": 24.56546761840582, "count": 249, "self": 24.56546761840582 }, "TrainerController.advance": { "total": 117761.21391058713, "count": 3252957, "self": 53.66396142542362, "children": { "env_step": { "total": 55676.000531986356, "count": 3252957, "self": 43812.915923289955, "children": { "SubprocessEnvManager._take_step": { "total": 11831.879136480391, "count": 3252957, "self": 426.82750248908997, "children": { "TorchPolicy.evaluate": { "total": 11405.051633991301, "count": 6462430, "self": 11405.051633991301 } } }, "workers": { "total": 31.205472216010094, "count": 3252957, "self": 0.0, "children": { "worker_root": { "total": 117734.94591672719, "count": 3252957, "is_parallel": true, "self": 81630.8699169308, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027211830019950867, "count": 2, "is_parallel": true, "self": 0.000684984028339386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020361989736557007, "count": 8, "is_parallel": true, "self": 0.0020361989736557007 } } }, "UnityEnvironment.step": { "total": 0.02486460655927658, "count": 1, "is_parallel": true, "self": 0.0005846098065376282, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047321617603302, "count": 1, "is_parallel": true, "self": 0.00047321617603302 }, "communicator.exchange": { "total": 0.021958790719509125, "count": 1, "is_parallel": true, "self": 0.021958790719509125 }, "steps_from_proto": { "total": 0.0018479898571968079, "count": 2, "is_parallel": true, "self": 0.0003945678472518921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014534220099449158, "count": 8, "is_parallel": true, "self": 0.0014534220099449158 } } } } } } }, "UnityEnvironment.step": { "total": 36103.5907208547, "count": 3252956, "is_parallel": true, "self": 1735.802337884903, "children": { "UnityEnvironment._generate_step_input": { "total": 1249.075766555965, "count": 3252956, "is_parallel": true, "self": 1249.075766555965 }, "communicator.exchange": { "total": 27656.65300156176, "count": 3252956, "is_parallel": true, "self": 27656.65300156176 }, "steps_from_proto": { "total": 5462.059614852071, "count": 6505912, "is_parallel": true, "self": 1043.9579699635506, "children": { "_process_rank_one_or_two_observation": { "total": 4418.10164488852, "count": 26023648, "is_parallel": true, "self": 4418.10164488852 } } } } }, "steps_from_proto": { "total": 0.4852789416909218, "count": 496, "is_parallel": true, "self": 0.09975766390562057, "children": { "_process_rank_one_or_two_observation": { "total": 0.3855212777853012, "count": 1984, "is_parallel": true, "self": 0.3855212777853012 } } } } } } } } }, "trainer_advance": { "total": 62031.54941717535, "count": 3252957, "self": 635.0691465362906, "children": { "process_trajectory": { "total": 6193.857440367341, "count": 3252957, "self": 6172.539449818432, "children": { "RLTrainer._checkpoint": { "total": 21.31799054890871, "count": 100, "self": 21.31799054890871 } } }, "_update_policy": { "total": 55202.62283027172, "count": 2287, "self": 6496.640734091401, "children": { "TorchPOCAOptimizer.update": { "total": 48705.98209618032, "count": 68613, "self": 48705.98209618032 } } } } } } }, "trainer_threads": { "total": 1.3634562492370605e-06, "count": 1, "self": 1.3634562492370605e-06 }, "TrainerController._save_models": { "total": 0.21691541373729706, "count": 1, "self": 0.009875722229480743, "children": { "RLTrainer._checkpoint": { "total": 0.20703969150781631, "count": 1, "self": 0.20703969150781631 } } } } } } }