{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.132916212081909, "min": 3.114339828491211, "max": 3.2956509590148926, "count": 145 }, "SoccerTwos.Policy.Entropy.sum": { "value": 91130.265625, "min": 20439.837890625, "max": 132276.75, "count": 145 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 446.625, "max": 999.0, "count": 145 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 14292.0, "max": 27668.0, "count": 145 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1205.447104541799, "min": 1198.949432231278, "max": 1208.6909132956919, "count": 71 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2410.894209083598, "min": 2401.2944941576525, "max": 16785.29205123789, "count": 71 }, "SoccerTwos.Step.mean": { "value": 1449032.0, "min": 9850.0, "max": 1449032.0, "count": 145 }, "SoccerTwos.Step.sum": { "value": 1449032.0, "min": 9850.0, "max": 1449032.0, "count": 145 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0011964114382863045, "min": -0.07850208878517151, "max": 0.00928493868559599, "count": 145 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.011964114382863045, "min": -1.4130375385284424, "max": 0.09284938871860504, "count": 145 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0009966209763661027, "min": -0.07855098694562912, "max": 0.00917109102010727, "count": 145 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.009966209530830383, "min": -1.4139177799224854, "max": 0.09171091020107269, "count": 145 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 145 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 145 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6191200017929077, "max": 0.18149999777475992, "count": 145 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -9.286800026893616, "max": 2.3231998682022095, "count": 145 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6191200017929077, "max": 0.18149999777475992, "count": 145 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -9.286800026893616, "max": 2.3231998682022095, "count": 145 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 145 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 145 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013722244869131827, "min": 0.010793852678034455, "max": 0.022973678012688955, "count": 67 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013722244869131827, "min": 0.010793852678034455, "max": 0.022973678012688955, "count": 67 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.0684805874916493e-05, "min": 2.8202668289623034e-07, "max": 0.005947487133865555, "count": 67 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.0684805874916493e-05, "min": 2.8202668289623034e-07, "max": 0.005947487133865555, "count": 67 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.0265956067693575e-05, "min": 2.835336933533957e-07, "max": 0.0058849061063180365, "count": 67 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.0265956067693575e-05, "min": 2.835336933533957e-07, "max": 0.0058849061063180365, "count": 67 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 67 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 67 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 67 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 67 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 67 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 67 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693525227", "python_version": "3.9.6 (default, May 7 2023, 23:32:44) \n[Clang 14.0.3 (clang-1403.0.22.14.1)]", "command_line_arguments": "/Users/stevenkaram/.local/share/virtualenvs/mlagents-4lvf3fE2/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1693530791" }, "total": 5563.463750041, "count": 1, "self": 0.1040249159996165, "children": { "run_training.setup": { "total": 0.04398325000000014, "count": 1, "self": 0.04398325000000014 }, "TrainerController.start_learning": { "total": 5563.315741875001, "count": 1, "self": 1.0611064640943368, "children": { "TrainerController._reset_env": { "total": 3.8875917910001614, "count": 8, "self": 3.8875917910001614 }, "TrainerController.advance": { "total": 5558.197535660906, "count": 95089, "self": 1.006084920891226, "children": { "env_step": { "total": 4465.822151714929, "count": 95089, "self": 4298.762876369955, "children": { "SubprocessEnvManager._take_step": { "total": 166.38352321301554, "count": 95089, "self": 5.438212866933554, "children": { "TorchPolicy.evaluate": { "total": 160.94531034608198, "count": 188988, "self": 160.94531034608198 } } }, "workers": { "total": 0.6757521319582285, "count": 95089, "self": 0.0, "children": { "worker_root": { "total": 5548.638626796078, "count": 95089, "is_parallel": true, "self": 1404.9407939500143, "children": { "steps_from_proto": { "total": 0.010491376001160013, "count": 16, "is_parallel": true, "self": 0.0015227949983875888, "children": { "_process_rank_one_or_two_observation": { "total": 0.008968581002772424, "count": 64, "is_parallel": true, "self": 0.008968581002772424 } } }, "UnityEnvironment.step": { "total": 4143.687341470062, "count": 95089, "is_parallel": true, "self": 11.593570768973223, "children": { "UnityEnvironment._generate_step_input": { "total": 66.60704460194432, "count": 95089, "is_parallel": true, "self": 66.60704460194432 }, "communicator.exchange": { "total": 3941.2416235450596, "count": 95089, "is_parallel": true, "self": 3941.2416235450596 }, "steps_from_proto": { "total": 124.24510255408467, "count": 190178, "is_parallel": true, "self": 17.13218506095953, "children": { "_process_rank_one_or_two_observation": { "total": 107.11291749312514, "count": 760712, "is_parallel": true, "self": 107.11291749312514 } } } } } } } } } } }, "trainer_advance": { "total": 1091.3692990250863, "count": 95089, "self": 9.776713466147157, "children": { "process_trajectory": { "total": 151.77031234594142, "count": 95089, "self": 151.4485743039411, "children": { "RLTrainer._checkpoint": { "total": 0.32173804200033373, "count": 2, "self": 0.32173804200033373 } } }, "_update_policy": { "total": 929.8222732129977, "count": 68, "self": 133.9601656730099, "children": { "TorchPOCAOptimizer.update": { "total": 795.8621075399878, "count": 2030, "self": 795.8621075399878 } } } } } } }, "trainer_threads": { "total": 6.669997674180195e-07, "count": 1, "self": 6.669997674180195e-07 }, "TrainerController._save_models": { "total": 0.16950729200016212, "count": 1, "self": 0.002447292000397283, "children": { "RLTrainer._checkpoint": { "total": 0.16705999999976484, "count": 1, "self": 0.16705999999976484 } } } } } } }