{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.259511709213257, "min": 3.259511709213257, "max": 3.295741319656372, "count": 16 }, "SoccerTwos.Policy.Entropy.sum": { "value": 90953.4140625, "min": 28942.8203125, "max": 106412.890625, "count": 16 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 791.5714285714286, "min": 521.8, "max": 999.0, "count": 16 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22164.0, "min": 16944.0, "max": 22372.0, "count": 16 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.6922331469073, "min": 1191.6922331469073, "max": 1197.6300552796083, "count": 13 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9533.537865175258, "min": 2384.9430510499333, "max": 19152.344780022133, "count": 13 }, "SoccerTwos.Step.mean": { "value": 159596.0, "min": 9479.0, "max": 159596.0, "count": 16 }, "SoccerTwos.Step.sum": { "value": 159596.0, "min": 9479.0, "max": 159596.0, "count": 16 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.013069055043160915, "min": 0.013069055043160915, "max": 0.10185398161411285, "count": 16 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.16989772021770477, "min": 0.16989772021770477, "max": 1.9351274967193604, "count": 16 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.012426543980836868, "min": 0.012426543980836868, "max": 0.10180485993623734, "count": 16 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.161545068025589, "min": 0.161545068025589, "max": 1.934121012687683, "count": 16 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 16 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 16 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.44252307598407453, "min": -0.5370736812290392, "max": 0.03303999900817871, "count": 16 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.752799987792969, "min": -10.204399943351746, "max": 0.3303999900817871, "count": 16 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.44252307598407453, "min": -0.5370736812290392, "max": 0.03303999900817871, "count": 16 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.752799987792969, "min": -10.204399943351746, "max": 0.3303999900817871, "count": 16 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01770546785288995, "min": 0.012537877772532131, "max": 0.021505475727220377, "count": 7 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01770546785288995, "min": 0.012537877772532131, "max": 0.021505475727220377, "count": 7 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0023161553932974734, "min": 0.0007440834905234321, "max": 0.008842417830601334, "count": 7 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0023161553932974734, "min": 0.0007440834905234321, "max": 0.008842417830601334, "count": 7 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002326815548197677, "min": 0.0007457728771745072, "max": 0.00819348266037802, "count": 7 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002326815548197677, "min": 0.0007457728771745072, "max": 0.00819348266037802, "count": 7 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 7 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 7 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 7 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 7 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 7 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680387416", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:24) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/clementthiriet/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --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", "numpy_version": "1.21.2", "end_time_seconds": "1680388079" }, "total": 663.4638185, "count": 1, "self": 0.12192162500002723, "children": { "run_training.setup": { "total": 0.060317459000000184, "count": 1, "self": 0.060317459000000184 }, "TrainerController.start_learning": { "total": 663.281579416, "count": 1, "self": 0.1281013870013794, "children": { "TrainerController._reset_env": { "total": 2.4665004999999987, "count": 1, "self": 2.4665004999999987 }, "TrainerController.advance": { "total": 660.5726466129985, "count": 10992, "self": 0.11882123999976102, "children": { "env_step": { "total": 548.1723853380014, "count": 10992, "self": 528.0303609479998, "children": { "SubprocessEnvManager._take_step": { "total": 20.04637094500028, "count": 10992, "self": 0.5218304509988592, "children": { "TorchPolicy.evaluate": { "total": 19.52454049400142, "count": 21828, "self": 19.52454049400142 } } }, "workers": { "total": 0.09565344500122208, "count": 10991, "self": 0.0, "children": { "worker_root": { "total": 660.4438563540028, "count": 10991, "is_parallel": true, "self": 151.742179689002, "children": { "steps_from_proto": { "total": 0.001600126000000035, "count": 2, "is_parallel": true, "self": 0.0002107099999992812, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013894160000007538, "count": 8, "is_parallel": true, "self": 0.0013894160000007538 } } }, "UnityEnvironment.step": { "total": 508.7000765390008, "count": 10991, "is_parallel": true, "self": 1.4707369160045118, "children": { "UnityEnvironment._generate_step_input": { "total": 8.72545943800057, "count": 10991, "is_parallel": true, "self": 8.72545943800057 }, "communicator.exchange": { "total": 478.93568528000037, "count": 10991, "is_parallel": true, "self": 478.93568528000037 }, "steps_from_proto": { "total": 19.568194904995302, "count": 21982, "is_parallel": true, "self": 2.135017521992289, "children": { "_process_rank_one_or_two_observation": { "total": 17.433177383003013, "count": 87928, "is_parallel": true, "self": 17.433177383003013 } } } } } } } } } } }, "trainer_advance": { "total": 112.28144003499737, "count": 10991, "self": 0.9418736109951027, "children": { "process_trajectory": { "total": 18.29796225700239, "count": 10991, "self": 18.29796225700239 }, "_update_policy": { "total": 93.04160416699987, "count": 7, "self": 11.6692971599999, "children": { "TorchPOCAOptimizer.update": { "total": 81.37230700699997, "count": 210, "self": 81.37230700699997 } } } } } } }, "trainer_threads": { "total": 6.24999984211172e-07, "count": 1, "self": 6.24999984211172e-07 }, "TrainerController._save_models": { "total": 0.11433029100010117, "count": 1, "self": 0.0006430830001136201, "children": { "RLTrainer._checkpoint": { "total": 0.11368720799998755, "count": 1, "self": 0.11368720799998755 } } } } } } }