{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.775998592376709, "min": 1.6040146350860596, "max": 3.2957441806793213, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35747.30078125, "min": 5111.42138671875, "max": 138394.046875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 82.56666666666666, "min": 55.28888888888889, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19816.0, "min": 15564.0, "max": 24952.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1573.510181424287, "min": 1176.3367770620202, "max": 1643.2444482422695, "count": 2891 }, "SoccerTwos.Self-play.ELO.sum": { "value": 188821.22177091445, "min": 2354.063791122488, "max": 291336.48131911457, "count": 2891 }, "SoccerTwos.Step.mean": { "value": 49999865.0, "min": 9498.0, "max": 49999865.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999865.0, "min": 9498.0, "max": 49999865.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06021175906062126, "min": -0.29010486602783203, "max": 0.12045252323150635, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.2254109382629395, "min": -18.919986724853516, "max": 9.369237899780273, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05843336135149002, "min": -0.29126614332199097, "max": 0.12659993767738342, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.012003421783447, "min": -19.16312026977539, "max": 9.595020294189453, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06249999751647314, "min": -0.8743764705517713, "max": 0.6009942889213562, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.499999701976776, "min": -55.73639988899231, "max": 43.6576002240181, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06249999751647314, "min": -0.8743764705517713, "max": 0.6009942889213562, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.499999701976776, "min": -55.73639988899231, "max": 43.6576002240181, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016774558438919486, "min": 0.010072278234777817, "max": 0.025630577544992168, "count": 2341 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016774558438919486, "min": 0.010072278234777817, "max": 0.025630577544992168, "count": 2341 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09155314341187477, "min": 3.240071249493992e-11, "max": 0.09859520792961121, "count": 2341 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09155314341187477, "min": 3.240071249493992e-11, "max": 0.09859520792961121, "count": 2341 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09291486019889514, "min": 4.150054478309813e-11, "max": 0.10025302891929945, "count": 2341 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09291486019889514, "min": 4.150054478309813e-11, "max": 0.10025302891929945, "count": 2341 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2341 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2341 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2341 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2341 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2341 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2341 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703464603", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\chang\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --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": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1703627288" }, "total": 162713.8910461, "count": 1, "self": 2.877047700021649, "children": { "run_training.setup": { "total": 0.10487579999971786, "count": 1, "self": 0.10487579999971786 }, "TrainerController.start_learning": { "total": 162710.9091226, "count": 1, "self": 95.03098711458733, "children": { "TrainerController._reset_env": { "total": 22.870975599962094, "count": 250, "self": 22.870975599962094 }, "TrainerController.advance": { "total": 162592.78000478543, "count": 3285140, "self": 99.11501299220254, "children": { "env_step": { "total": 66458.05725349297, "count": 3285140, "self": 49901.25500668623, "children": { "SubprocessEnvManager._take_step": { "total": 16496.2410986158, "count": 3285140, "self": 579.729718210041, "children": { "TorchPolicy.evaluate": { "total": 15916.511380405758, "count": 6413848, "self": 15916.511380405758 } } }, "workers": { "total": 60.56114819093136, "count": 3285140, "self": 0.0, "children": { "worker_root": { "total": 162593.12074150195, "count": 3285140, "is_parallel": true, "self": 124623.27507769279, "children": { "steps_from_proto": { "total": 0.5632270000055541, "count": 500, "is_parallel": true, "self": 0.10653560005812324, "children": { "_process_rank_one_or_two_observation": { "total": 0.4566913999474309, "count": 2000, "is_parallel": true, "self": 0.4566913999474309 } } }, "UnityEnvironment.step": { "total": 37969.28243680915, "count": 3285140, "is_parallel": true, "self": 2018.8212593716598, "children": { "UnityEnvironment._generate_step_input": { "total": 2098.5394663058187, "count": 3285140, "is_parallel": true, "self": 2098.5394663058187 }, "communicator.exchange": { "total": 26754.034175819048, "count": 3285140, "is_parallel": true, "self": 26754.034175819048 }, "steps_from_proto": { "total": 7097.887535312628, "count": 6570280, "is_parallel": true, "self": 1349.507690489363, "children": { "_process_rank_one_or_two_observation": { "total": 5748.379844823265, "count": 26281120, "is_parallel": true, "self": 5748.379844823265 } } } } } } } } } } }, "trainer_advance": { "total": 96035.60773830024, "count": 3285140, "self": 705.0338465059904, "children": { "process_trajectory": { "total": 13425.446054794105, "count": 3285140, "self": 13407.045061593923, "children": { "RLTrainer._checkpoint": { "total": 18.40099320018271, "count": 100, "self": 18.40099320018271 } } }, "_update_policy": { "total": 81905.12783700015, "count": 2341, "self": 8293.239140300793, "children": { "TorchPOCAOptimizer.update": { "total": 73611.88869669936, "count": 70230, "self": 73611.88869669936 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.227154199994402, "count": 1, "self": 0.05800160000217147, "children": { "RLTrainer._checkpoint": { "total": 0.16915259999223053, "count": 1, "self": 0.16915259999223053 } } } } } } }