{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.751165509223938, "min": 1.7281851768493652, "max": 3.295750379562378, "count": 2142 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36031.98046875, "min": 26314.73828125, "max": 121404.546875, "count": 2142 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.76470588235294, "min": 41.813559322033896, "max": 999.0, "count": 2142 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 8312.0, "max": 27596.0, "count": 2142 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1693.05946970254, "min": 1187.3060552060288, "max": 1708.121337737342, "count": 2044 }, "SoccerTwos.Self-play.ELO.sum": { "value": 287820.1098494318, "min": 2375.907531902884, "max": 382607.9029890414, "count": 2044 }, "SoccerTwos.Step.mean": { "value": 21419873.0, "min": 9816.0, "max": 21419873.0, "count": 2142 }, "SoccerTwos.Step.sum": { "value": 21419873.0, "min": 9816.0, "max": 21419873.0, "count": 2142 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011743778362870216, "min": -0.1494860053062439, "max": 0.18101388216018677, "count": 2142 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.9964423179626465, "min": -23.959697723388672, "max": 30.886472702026367, "count": 2142 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.011528833769261837, "min": -0.15096309781074524, "max": 0.18238456547260284, "count": 2142 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.9599018096923828, "min": -23.71039581298828, "max": 30.490951538085938, "count": 2142 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2142 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2142 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.13288352945271661, "min": -0.5454545454545454, "max": 0.49303000047802925, "count": 2142 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 22.590200006961823, "min": -56.025999903678894, "max": 70.69039952754974, "count": 2142 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.13288352945271661, "min": -0.5454545454545454, "max": 0.49303000047802925, "count": 2142 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 22.590200006961823, "min": -56.025999903678894, "max": 70.69039952754974, "count": 2142 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2142 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2142 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012627485244593117, "min": 0.005336672674942141, "max": 0.02139821903159221, "count": 1032 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012627485244593117, "min": 0.005336672674942141, "max": 0.02139821903159221, "count": 1032 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10851541062196096, "min": 2.6814518131838363e-08, "max": 0.13476883371671042, "count": 1032 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10851541062196096, "min": 2.6814518131838363e-08, "max": 0.13476883371671042, "count": 1032 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10898871471484502, "min": 5.799040891929508e-08, "max": 0.13534838755925496, "count": 1032 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10898871471484502, "min": 5.799040891929508e-08, "max": 0.13534838755925496, "count": 1032 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00029, "min": 0.00029, "max": 0.00029000000000000006, "count": 1032 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00029, "min": 0.00029, "max": 0.00029000000000000006, "count": 1032 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.21, "min": 0.21, "max": 0.21, "count": 1032 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.21, "min": 0.21, "max": 0.21, "count": 1032 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005099999999999999, "min": 0.005099999999999999, "max": 0.0050999999999999995, "count": 1032 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005099999999999999, "min": 0.005099999999999999, "max": 0.0050999999999999995, "count": 1032 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676388836", "python_version": "3.9.9 (main, Feb 15 2023, 00:04:22) \n[GCC 11.3.0]", "command_line_arguments": "/home/gpu/venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../training-envs-executables/linux/SoccerTwos.x86_64 --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": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1676424499" }, "total": 35661.719598334, "count": 1, "self": 0.21976863899908494, "children": { "run_training.setup": { "total": 0.016842687997268513, "count": 1, "self": 0.016842687997268513 }, "TrainerController.start_learning": { "total": 35661.482987007, "count": 1, "self": 23.228275687979476, "children": { "TrainerController._reset_env": { "total": 3.8907350710142055, "count": 107, "self": 3.8907350710142055 }, "TrainerController.advance": { "total": 35634.221033468006, "count": 1465081, "self": 23.17699482966418, "children": { "env_step": { "total": 27149.61896410377, "count": 1465081, "self": 17218.898069075738, "children": { "SubprocessEnvManager._take_step": { "total": 9916.93967805567, "count": 1465081, "self": 138.47342591667257, "children": { "TorchPolicy.evaluate": { "total": 9778.466252138998, "count": 2699379, "self": 9778.466252138998 } } }, "workers": { "total": 13.781216972362017, "count": 1465080, "self": 0.0, "children": { "worker_root": { "total": 35607.7948638117, "count": 1465080, "is_parallel": true, "self": 21069.751659738664, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017199099966092035, "count": 2, "is_parallel": true, "self": 0.0004666889872169122, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012532210093922913, "count": 8, "is_parallel": true, "self": 0.0012532210093922913 } } }, "UnityEnvironment.step": { "total": 0.019728951003344264, "count": 1, "is_parallel": true, "self": 0.00039803200343158096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003727509974851273, "count": 1, "is_parallel": true, "self": 0.0003727509974851273 }, "communicator.exchange": { "total": 0.017740227005560882, "count": 1, "is_parallel": true, "self": 0.017740227005560882 }, "steps_from_proto": { "total": 0.0012179409968666732, "count": 2, "is_parallel": true, "self": 0.0002811619924614206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009367790044052526, "count": 8, "is_parallel": true, "self": 0.0009367790044052526 } } } } } } }, "UnityEnvironment.step": { "total": 14537.912768843868, "count": 1465079, "is_parallel": true, "self": 553.3181830873509, "children": { "UnityEnvironment._generate_step_input": { "total": 346.30558454406855, "count": 1465079, "is_parallel": true, "self": 346.30558454406855 }, "communicator.exchange": { "total": 12028.862156003051, "count": 1465079, "is_parallel": true, "self": 12028.862156003051 }, "steps_from_proto": { "total": 1609.4268452093966, "count": 2930158, "is_parallel": true, "self": 343.6122466235902, "children": { "_process_rank_one_or_two_observation": { "total": 1265.8145985858064, "count": 11720632, "is_parallel": true, "self": 1265.8145985858064 } } } } }, "steps_from_proto": { "total": 0.13043522916996153, "count": 212, "is_parallel": true, "self": 0.028492074154200964, "children": { "_process_rank_one_or_two_observation": { "total": 0.10194315501576057, "count": 848, "is_parallel": true, "self": 0.10194315501576057 } } } } } } } } }, "trainer_advance": { "total": 8461.42507453457, "count": 1465080, "self": 192.51941794154118, "children": { "process_trajectory": { "total": 4103.265077095231, "count": 1465080, "self": 4097.194397743282, "children": { "RLTrainer._checkpoint": { "total": 6.070679351949366, "count": 42, "self": 6.070679351949366 } } }, "_update_policy": { "total": 4165.640579497798, "count": 1032, "self": 2752.84588046476, "children": { "TorchPOCAOptimizer.update": { "total": 1412.7946990330383, "count": 15483, "self": 1412.7946990330383 } } } } } } }, "trainer_threads": { "total": 9.100040188059211e-07, "count": 1, "self": 9.100040188059211e-07 }, "TrainerController._save_models": { "total": 0.14294186999904923, "count": 1, "self": 0.0008466799918096513, "children": { "RLTrainer._checkpoint": { "total": 0.14209519000723958, "count": 1, "self": 0.14209519000723958 } } } } } } }