{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.0681722164154053, "min": 3.0086112022399902, "max": 3.295736312866211, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 71083.4140625, "min": 13498.91015625, "max": 142699.484375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 759.3333333333334, "min": 381.8333333333333, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18224.0, "min": 11712.0, "max": 29128.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1230.7034147074687, "min": 1193.3253533041118, "max": 1232.0422570872072, "count": 366 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9845.62731765975, "min": 2388.817898597924, "max": 16908.562139028272, "count": 366 }, "SoccerTwos.Step.mean": { "value": 4999774.0, "min": 9582.0, "max": 4999774.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999774.0, "min": 9582.0, "max": 4999774.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.005820202175527811, "min": -0.028853941708803177, "max": 0.01749301701784134, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.07566262781620026, "min": -0.48075154423713684, "max": 0.2367807775735855, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00484585203230381, "min": -0.034612782299518585, "max": 0.018317358568310738, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.06299607455730438, "min": -0.5254640579223633, "max": 0.24662959575653076, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0010307729244232178, "min": -0.5625, "max": 0.4507555663585663, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.013400048017501831, "min": -9.0, "max": 8.113600194454193, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0010307729244232178, "min": -0.5625, "max": 0.4507555663585663, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.013400048017501831, "min": -9.0, "max": 8.113600194454193, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022048475802876055, "min": 0.010168385475920635, "max": 0.024457173788687215, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022048475802876055, "min": 0.010168385475920635, "max": 0.024457173788687215, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.001593428628014711, "min": 8.304267803775171e-08, "max": 0.006287430979621907, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.001593428628014711, "min": 8.304267803775171e-08, "max": 0.006287430979621907, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0016020291184152787, "min": 1.1614907980591246e-07, "max": 0.006288486144815882, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0016020291184152787, "min": 1.1614907980591246e-07, "max": 0.006288486144815882, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692751022", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/agustin/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692755762" }, "total": 4740.917500071999, "count": 1, "self": 0.16804642299939587, "children": { "run_training.setup": { "total": 0.007140761999835377, "count": 1, "self": 0.007140761999835377 }, "TrainerController.start_learning": { "total": 4740.742312887, "count": 1, "self": 4.629413993542585, "children": { "TrainerController._reset_env": { "total": 3.6082590109936064, "count": 25, "self": 3.6082590109936064 }, "TrainerController.advance": { "total": 4732.361187622464, "count": 325378, "self": 4.668138948884916, "children": { "env_step": { "total": 3580.960536827044, "count": 325378, "self": 2540.381440856753, "children": { "SubprocessEnvManager._take_step": { "total": 1037.7594984670468, "count": 325378, "self": 26.679753365224315, "children": { "TorchPolicy.evaluate": { "total": 1011.0797451018225, "count": 646028, "self": 1011.0797451018225 } } }, "workers": { "total": 2.81959750324404, "count": 325378, "self": 0.0, "children": { "worker_root": { "total": 4734.714342336447, "count": 325378, "is_parallel": true, "self": 2717.457386475794, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015060519999678945, "count": 2, "is_parallel": true, "self": 0.0003789260017583729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011271259982095216, "count": 8, "is_parallel": true, "self": 0.0011271259982095216 } } }, "UnityEnvironment.step": { "total": 0.015841564999391267, "count": 1, "is_parallel": true, "self": 0.00035892199866793817, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002934660005848855, "count": 1, "is_parallel": true, "self": 0.0002934660005848855 }, "communicator.exchange": { "total": 0.014033939000000828, "count": 1, "is_parallel": true, "self": 0.014033939000000828 }, "steps_from_proto": { "total": 0.001155238000137615, "count": 2, "is_parallel": true, "self": 0.00025357500089739915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009016629992402159, "count": 8, "is_parallel": true, "self": 0.0009016629992402159 } } } } } } }, "UnityEnvironment.step": { "total": 2017.229015981664, "count": 325377, "is_parallel": true, "self": 116.31933354324883, "children": { "UnityEnvironment._generate_step_input": { "total": 83.54269948724595, "count": 325377, "is_parallel": true, "self": 83.54269948724595 }, "communicator.exchange": { "total": 1450.5245641430774, "count": 325377, "is_parallel": true, "self": 1450.5245641430774 }, "steps_from_proto": { "total": 366.8424188080917, "count": 650754, "is_parallel": true, "self": 76.60866541693667, "children": { "_process_rank_one_or_two_observation": { "total": 290.233753391155, "count": 2603016, "is_parallel": true, "self": 290.233753391155 } } } } }, "steps_from_proto": { "total": 0.027939878988945566, "count": 48, "is_parallel": true, "self": 0.0059418999935587635, "children": { "_process_rank_one_or_two_observation": { "total": 0.021997978995386802, "count": 192, "is_parallel": true, "self": 0.021997978995386802 } } } } } } } } }, "trainer_advance": { "total": 1146.732511846535, "count": 325378, "self": 35.44267001867229, "children": { "process_trajectory": { "total": 269.43742016885517, "count": 325378, "self": 267.9769432328576, "children": { "RLTrainer._checkpoint": { "total": 1.4604769359975762, "count": 10, "self": 1.4604769359975762 } } }, "_update_policy": { "total": 841.8524216590076, "count": 232, "self": 517.9916511429892, "children": { "TorchPOCAOptimizer.update": { "total": 323.8607705160184, "count": 6960, "self": 323.8607705160184 } } } } } } }, "trainer_threads": { "total": 5.700003384845331e-07, "count": 1, "self": 5.700003384845331e-07 }, "TrainerController._save_models": { "total": 0.14345168999898306, "count": 1, "self": 0.0011678609989758115, "children": { "RLTrainer._checkpoint": { "total": 0.14228382900000724, "count": 1, "self": 0.14228382900000724 } } } } } } }