{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.6568377017974854, "min": 2.3778088092803955, "max": 3.2957394123077393, "count": 520 }, "SoccerTwos.Policy.Entropy.sum": { "value": 62743.87890625, "min": 19785.4453125, "max": 122762.734375, "count": 520 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 484.5, "max": 999.0, "count": 520 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 16324.0, "max": 26028.0, "count": 520 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1179.3263696680078, "min": 1179.3263696680078, "max": 1200.5084590065987, "count": 118 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2358.6527393360157, "min": 2358.6527393360157, "max": 14290.673769686424, "count": 118 }, "SoccerTwos.Step.mean": { "value": 5199654.0, "min": 9000.0, "max": 5199654.0, "count": 520 }, "SoccerTwos.Step.sum": { "value": 5199654.0, "min": 9000.0, "max": 5199654.0, "count": 520 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 1.6559739378863014e-05, "min": -0.07629846036434174, "max": 0.033267658203840256, "count": 520 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.00016559739015065134, "min": -0.762984573841095, "max": 0.465747207403183, "count": 520 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 1.719225474516861e-05, "min": -0.07649959623813629, "max": 0.03332311287522316, "count": 520 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0001719225401757285, "min": -0.7649959921836853, "max": 0.46652355790138245, "count": 520 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 520 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 520 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5747333334551917, "max": 0.20083333055178323, "count": 520 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -10.345200002193451, "max": 2.409999966621399, "count": 520 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5747333334551917, "max": 0.20083333055178323, "count": 520 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -10.345200002193451, "max": 2.409999966621399, "count": 520 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 520 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 520 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016541421851919345, "min": 0.011152800204581582, "max": 0.024478018279963484, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016541421851919345, "min": 0.011152800204581582, "max": 0.024478018279963484, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.5423384434712186e-09, "min": 2.502632789891379e-09, "max": 0.006235445958251754, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.5423384434712186e-09, "min": 2.502632789891379e-09, "max": 0.006235445958251754, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 3.6848774550198487e-09, "min": 3.5078259260264606e-09, "max": 0.006302734573061268, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 3.6848774550198487e-09, "min": 3.5078259260264606e-09, "max": 0.006302734573061268, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699548250", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/dergky/anaconda3/envs/rl_unit7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu121", "numpy_version": "1.23.4", "end_time_seconds": "1699558764" }, "total": 10513.779172357004, "count": 1, "self": 0.1360064929976943, "children": { "run_training.setup": { "total": 0.015541163003945258, "count": 1, "self": 0.015541163003945258 }, "TrainerController.start_learning": { "total": 10513.627624701003, "count": 1, "self": 4.878290815366199, "children": { "TrainerController._reset_env": { "total": 1.906018714995298, "count": 11, "self": 1.906018714995298 }, "TrainerController.advance": { "total": 10506.710686128645, "count": 333472, "self": 4.2417537976944, "children": { "env_step": { "total": 5724.691368693966, "count": 333472, "self": 4957.396792501815, "children": { "SubprocessEnvManager._take_step": { "total": 763.9723277102094, "count": 333472, "self": 26.10670724528609, "children": { "TorchPolicy.evaluate": { "total": 737.8656204649233, "count": 662130, "self": 737.8656204649233 } } }, "workers": { "total": 3.3222484819416422, "count": 333471, "self": 0.0, "children": { "worker_root": { "total": 10505.352342732891, "count": 333471, "is_parallel": true, "self": 6192.198077794805, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012092445998860057, "count": 2, "is_parallel": true, "self": 0.009074285990209319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030181600086507387, "count": 8, "is_parallel": true, "self": 0.0030181600086507387 } } }, "UnityEnvironment.step": { "total": 0.02025621399661759, "count": 1, "is_parallel": true, "self": 0.0007955609980854206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005793570016976446, "count": 1, "is_parallel": true, "self": 0.0005793570016976446 }, "communicator.exchange": { "total": 0.01682428899948718, "count": 1, "is_parallel": true, "self": 0.01682428899948718 }, "steps_from_proto": { "total": 0.0020570069973473437, "count": 2, "is_parallel": true, "self": 0.00034916400181828067, "children": { "_process_rank_one_or_two_observation": { "total": 0.001707842995529063, "count": 8, "is_parallel": true, "self": 0.001707842995529063 } } } } } } }, "UnityEnvironment.step": { "total": 4313.129926345064, "count": 333470, "is_parallel": true, "self": 290.74589544362243, "children": { "UnityEnvironment._generate_step_input": { "total": 181.5000733290508, "count": 333470, "is_parallel": true, "self": 181.5000733290508 }, "communicator.exchange": { "total": 3055.2997629661913, "count": 333470, "is_parallel": true, "self": 3055.2997629661913 }, "steps_from_proto": { "total": 785.5841946061992, "count": 666940, "is_parallel": true, "self": 112.52890249548363, "children": { "_process_rank_one_or_two_observation": { "total": 673.0552921107155, "count": 2667760, "is_parallel": true, "self": 673.0552921107155 } } } } }, "steps_from_proto": { "total": 0.024338593022548594, "count": 20, "is_parallel": true, "self": 0.0035308739898027852, "children": { "_process_rank_one_or_two_observation": { "total": 0.02080771903274581, "count": 80, "is_parallel": true, "self": 0.02080771903274581 } } } } } } } } }, "trainer_advance": { "total": 4777.777563636984, "count": 333471, "self": 53.08873366556509, "children": { "process_trajectory": { "total": 663.7247087152937, "count": 333471, "self": 662.2671407102898, "children": { "RLTrainer._checkpoint": { "total": 1.45756800500385, "count": 10, "self": 1.45756800500385 } } }, "_update_policy": { "total": 4060.9641212561255, "count": 238, "self": 487.37785652947787, "children": { "TorchPOCAOptimizer.update": { "total": 3573.5862647266476, "count": 7140, "self": 3573.5862647266476 } } } } } } }, "trainer_threads": { "total": 9.119976311922073e-07, "count": 1, "self": 9.119976311922073e-07 }, "TrainerController._save_models": { "total": 0.13262812999892049, "count": 1, "self": 0.00210117400274612, "children": { "RLTrainer._checkpoint": { "total": 0.13052695599617437, "count": 1, "self": 0.13052695599617437 } } } } } } }