{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1133804321289062, "min": 3.102661371231079, "max": 3.2957539558410645, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27597.00390625, "min": 25997.5390625, "max": 143487.828125, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 397.54545454545456, "min": 199.2608695652174, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17492.0, "min": 16480.0, "max": 25084.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1260.470114148714, "min": 1200.84953632169, "max": 1260.470114148714, "count": 92 }, "SoccerTwos.Self-play.ELO.sum": { "value": 20167.521826379423, "min": 2403.8802455184264, "max": 55031.69379006797, "count": 92 }, "SoccerTwos.Step.mean": { "value": 999941.0, "min": 9560.0, "max": 999941.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999941.0, "min": 9560.0, "max": 999941.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03812256455421448, "min": -0.03356579691171646, "max": 0.08793723583221436, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.8768189549446106, "min": -0.607160210609436, "max": 4.133049964904785, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.037627846002578735, "min": -0.031118910759687424, "max": 0.09117133915424347, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.8654404282569885, "min": -0.5502427816390991, "max": 4.28505277633667, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.30168695553489355, "min": -0.4842333334187667, "max": 0.5116765981024884, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.938799977302551, "min": -10.953200101852417, "max": 24.048800110816956, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.30168695553489355, "min": -0.4842333334187667, "max": 0.5116765981024884, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.938799977302551, "min": -10.953200101852417, "max": 24.048800110816956, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01982781187398359, "min": 0.011926824614056386, "max": 0.023017469389985005, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01982781187398359, "min": 0.011926824614056386, "max": 0.023017469389985005, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.021284908739229044, "min": 4.099821368678628e-05, "max": 0.022463938097159068, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.021284908739229044, "min": 4.099821368678628e-05, "max": 0.022463938097159068, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.02187429883827766, "min": 4.1442839938099495e-05, "max": 0.02337551526725292, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.02187429883827766, "min": 4.1442839938099495e-05, "max": 0.02337551526725292, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723019403", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwosNew --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723021625" }, "total": 2221.40331031, "count": 1, "self": 0.442573055000139, "children": { "run_training.setup": { "total": 0.054269316000045364, "count": 1, "self": 0.054269316000045364 }, "TrainerController.start_learning": { "total": 2220.906467939, "count": 1, "self": 1.5256875920467792, "children": { "TrainerController._reset_env": { "total": 2.4312839539998095, "count": 5, "self": 2.4312839539998095 }, "TrainerController.advance": { "total": 2216.7255466939537, "count": 64894, "self": 1.681418279042191, "children": { "env_step": { "total": 1820.7204620000302, "count": 64894, "self": 1387.735235109335, "children": { "SubprocessEnvManager._take_step": { "total": 432.04261078575337, "count": 64894, "self": 12.062182696675336, "children": { "TorchPolicy.evaluate": { "total": 419.98042808907803, "count": 128466, "self": 419.98042808907803 } } }, "workers": { "total": 0.9426161049418624, "count": 64894, "self": 0.0, "children": { "worker_root": { "total": 2216.235230492861, "count": 64894, "is_parallel": true, "self": 1056.4223267198568, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003293138000117324, "count": 2, "is_parallel": true, "self": 0.0008867410006132559, "children": { "_process_rank_one_or_two_observation": { "total": 0.002406396999504068, "count": 8, "is_parallel": true, "self": 0.002406396999504068 } } }, "UnityEnvironment.step": { "total": 0.042546780000066065, "count": 1, "is_parallel": true, "self": 0.0012115459999222367, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008224739999604935, "count": 1, "is_parallel": true, "self": 0.0008224739999604935 }, "communicator.exchange": { "total": 0.03540516400016713, "count": 1, "is_parallel": true, "self": 0.03540516400016713 }, "steps_from_proto": { "total": 0.005107596000016201, "count": 2, "is_parallel": true, "self": 0.0005829379997521755, "children": { "_process_rank_one_or_two_observation": { "total": 0.004524658000264026, "count": 8, "is_parallel": true, "self": 0.004524658000264026 } } } } } } }, "UnityEnvironment.step": { "total": 1159.8032615460043, "count": 64893, "is_parallel": true, "self": 70.22577767103985, "children": { "UnityEnvironment._generate_step_input": { "total": 49.13416495598494, "count": 64893, "is_parallel": true, "self": 49.13416495598494 }, "communicator.exchange": { "total": 811.3958589559675, "count": 64893, "is_parallel": true, "self": 811.3958589559675 }, "steps_from_proto": { "total": 229.047459963012, "count": 129786, "is_parallel": true, "self": 37.85822161413034, "children": { "_process_rank_one_or_two_observation": { "total": 191.18923834888164, "count": 519144, "is_parallel": true, "self": 191.18923834888164 } } } } }, "steps_from_proto": { "total": 0.009642226999858394, "count": 8, "is_parallel": true, "self": 0.0018408130008538137, "children": { "_process_rank_one_or_two_observation": { "total": 0.0078014139990045805, "count": 32, "is_parallel": true, "self": 0.0078014139990045805 } } } } } } } } }, "trainer_advance": { "total": 394.32366641488125, "count": 64894, "self": 13.735710694818863, "children": { "process_trajectory": { "total": 112.82515536706251, "count": 64894, "self": 112.41186320606266, "children": { "RLTrainer._checkpoint": { "total": 0.4132921609998448, "count": 2, "self": 0.4132921609998448 } } }, "_update_policy": { "total": 267.7628003529999, "count": 46, "self": 158.34779366198472, "children": { "TorchPOCAOptimizer.update": { "total": 109.41500669101515, "count": 1380, "self": 109.41500669101515 } } } } } } }, "trainer_threads": { "total": 9.049999789567664e-07, "count": 1, "self": 9.049999789567664e-07 }, "TrainerController._save_models": { "total": 0.2239487939996252, "count": 1, "self": 0.0017336199998680968, "children": { "RLTrainer._checkpoint": { "total": 0.2222151739997571, "count": 1, "self": 0.2222151739997571 } } } } } } }