{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.7494909167289734, "min": 0.7274272441864014, "max": 3.295811891555786, "count": 2000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 14797.94921875, "min": 12973.8681640625, "max": 105465.96875, "count": 2000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.83132530120482, "min": 45.5188679245283, "max": 999.0, "count": 2000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19864.0, "min": 14736.0, "max": 25268.0, "count": 2000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1761.490137084402, "min": 1195.844794550754, "max": 1800.3034901610533, "count": 1998 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292407.3627560107, "min": 2399.4985597382833, "max": 378386.4566191012, "count": 1998 }, "SoccerTwos.Step.mean": { "value": 19999944.0, "min": 9652.0, "max": 19999944.0, "count": 2000 }, "SoccerTwos.Step.sum": { "value": 19999944.0, "min": 9652.0, "max": 19999944.0, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03484977036714554, "min": -0.13655488193035126, "max": 0.18776509165763855, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.7502121925354, "min": -19.800457000732422, "max": 24.784992218017578, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03535076603293419, "min": -0.1446973830461502, "max": 0.18393611907958984, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.832876682281494, "min": -20.981121063232422, "max": 24.25238800048828, "count": 2000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09759272842696219, "min": -0.6470588235294118, "max": 0.6544881351923538, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.10280019044876, "min": -57.34900003671646, "max": 61.02780032157898, "count": 2000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09759272842696219, "min": -0.6470588235294118, "max": 0.6544881351923538, "count": 2000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.10280019044876, "min": -57.34900003671646, "max": 61.02780032157898, "count": 2000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018186160400509833, "min": 0.011413839999950142, "max": 0.023963280958123504, "count": 970 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018186160400509833, "min": 0.011413839999950142, "max": 0.023963280958123504, "count": 970 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1014073920249939, "min": 0.0006905387435108423, "max": 0.12033649995923042, "count": 970 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1014073920249939, "min": 0.0006905387435108423, "max": 0.12033649995923042, "count": 970 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10152057856321335, "min": 0.0007671873888466507, "max": 0.1208409234881401, "count": 970 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10152057856321335, "min": 0.0007671873888466507, "max": 0.1208409234881401, "count": 970 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 5.8869980410007976e-08, "min": 5.8869980410007976e-08, "max": 0.00029969238010254, "count": 970 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 5.8869980410007976e-08, "min": 5.8869980410007976e-08, "max": 0.00029969238010254, "count": 970 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10001958999999999, "min": 0.10001958999999999, "max": 0.19989746000000008, "count": 970 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10001958999999999, "min": 0.10001958999999999, "max": 0.19989746000000008, "count": 970 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.0977541000000134e-05, "min": 1.0977541000000134e-05, "max": 0.004994883254, "count": 970 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.0977541000000134e-05, "min": 1.0977541000000134e-05, "max": 0.004994883254, "count": 970 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736525133", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/stefan/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos9 --no-graphics --torch-device cuda", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1736560686" }, "total": 35553.45176794598, "count": 1, "self": 0.36873860395280644, "children": { "run_training.setup": { "total": 0.010447545006172732, "count": 1, "self": 0.010447545006172732 }, "TrainerController.start_learning": { "total": 35553.07258179702, "count": 1, "self": 20.50890109487227, "children": { "TrainerController._reset_env": { "total": 2.5408188490837347, "count": 100, "self": 2.5408188490837347 }, "TrainerController.advance": { "total": 35529.84262374806, "count": 1373369, "self": 18.59447276283754, "children": { "env_step": { "total": 25630.410534975643, "count": 1373369, "self": 15407.643253953662, "children": { "SubprocessEnvManager._take_step": { "total": 10210.252099557867, "count": 1373369, "self": 119.48115686824895, "children": { "TorchPolicy.evaluate": { "total": 10090.770942689618, "count": 2511022, "self": 10090.770942689618 } } }, "workers": { "total": 12.515181464113994, "count": 1373369, "self": 0.0, "children": { "worker_root": { "total": 35511.73678986286, "count": 1373369, "is_parallel": true, "self": 22254.38950994931, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001703521003946662, "count": 2, "is_parallel": true, "self": 0.0004977550415787846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012057659623678774, "count": 8, "is_parallel": true, "self": 0.0012057659623678774 } } }, "UnityEnvironment.step": { "total": 0.01932847499847412, "count": 1, "is_parallel": true, "self": 0.00047046400140970945, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003157659957651049, "count": 1, "is_parallel": true, "self": 0.0003157659957651049 }, "communicator.exchange": { "total": 0.01738781700260006, "count": 1, "is_parallel": true, "self": 0.01738781700260006 }, "steps_from_proto": { "total": 0.0011544279986992478, "count": 2, "is_parallel": true, "self": 0.0002629169903229922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008915110083762556, "count": 8, "is_parallel": true, "self": 0.0008915110083762556 } } } } } } }, "UnityEnvironment.step": { "total": 13257.236389755388, "count": 1373368, "is_parallel": true, "self": 444.57447525358293, "children": { "UnityEnvironment._generate_step_input": { "total": 298.1148695660231, "count": 1373368, "is_parallel": true, "self": 298.1148695660231 }, "communicator.exchange": { "total": 11122.894891028845, "count": 1373368, "is_parallel": true, "self": 11122.894891028845 }, "steps_from_proto": { "total": 1391.6521539069363, "count": 2746736, "is_parallel": true, "self": 302.3874715605052, "children": { "_process_rank_one_or_two_observation": { "total": 1089.264682346431, "count": 10986944, "is_parallel": true, "self": 1089.264682346431 } } } } }, "steps_from_proto": { "total": 0.1108901581610553, "count": 198, "is_parallel": true, "self": 0.025228983722627163, "children": { "_process_rank_one_or_two_observation": { "total": 0.08566117443842813, "count": 792, "is_parallel": true, "self": 0.08566117443842813 } } } } } } } } }, "trainer_advance": { "total": 9880.83761600958, "count": 1373369, "self": 158.14742665737867, "children": { "process_trajectory": { "total": 4639.92850754768, "count": 1373369, "self": 4632.432310309639, "children": { "RLTrainer._checkpoint": { "total": 7.496197238040622, "count": 40, "self": 7.496197238040622 } } }, "_update_policy": { "total": 5082.761681804521, "count": 970, "self": 2451.060621449986, "children": { "TorchPOCAOptimizer.update": { "total": 2631.701060354535, "count": 48505, "self": 2631.701060354535 } } } } } } }, "trainer_threads": { "total": 8.399947546422482e-07, "count": 1, "self": 8.399947546422482e-07 }, "TrainerController._save_models": { "total": 0.18023726501269266, "count": 1, "self": 0.0019373390241526067, "children": { "RLTrainer._checkpoint": { "total": 0.17829992598854005, "count": 1, "self": 0.17829992598854005 } } } } } } }