{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.009624719619751, "min": 1.9668216705322266, "max": 3.295757532119751, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40964.19140625, "min": 26254.05859375, "max": 106385.9921875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.782051282051285, "min": 43.53982300884956, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19276.0, "min": 11548.0, "max": 29404.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1516.9327847519728, "min": 1198.9379579775102, "max": 1526.5037712662772, "count": 498 }, "SoccerTwos.Self-play.ELO.sum": { "value": 236641.51442130777, "min": 2397.9912087494063, "max": 335055.5667111251, "count": 498 }, "SoccerTwos.Step.mean": { "value": 4999997.0, "min": 9722.0, "max": 4999997.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999997.0, "min": 9722.0, "max": 4999997.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013239032588899136, "min": -0.10964519530534744, "max": 0.14397895336151123, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.0785281658172607, "min": -19.955425262451172, "max": 23.940650939941406, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.019041109830141068, "min": -0.11867866665124893, "max": 0.15647897124290466, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.9894542694091797, "min": -21.599517822265625, "max": 23.9058837890625, "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": 0.02148280288003812, "min": -0.472152380716233, "max": 0.46135593167806077, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.372800052165985, "min": -55.66520011425018, "max": 49.07179969549179, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.02148280288003812, "min": -0.472152380716233, "max": 0.46135593167806077, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.372800052165985, "min": -55.66520011425018, "max": 49.07179969549179, "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": 0.018792416494882978, "min": 0.010852588019527805, "max": 0.025696893265315643, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018792416494882978, "min": 0.010852588019527805, "max": 0.025696893265315643, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10439572110772133, "min": 0.0009845618905577188, "max": 0.11528145844737689, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10439572110772133, "min": 0.0009845618905577188, "max": 0.11528145844737689, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10584955861171087, "min": 0.0009898120236660664, "max": 0.11717152843872707, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10584955861171087, "min": 0.0009898120236660664, "max": 0.11717152843872707, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684151285", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/labicquette/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.0.1", "numpy_version": "1.21.5", "end_time_seconds": "1684159682" }, "total": 8397.292884086, "count": 1, "self": 0.16756035800062818, "children": { "run_training.setup": { "total": 0.007842205000088143, "count": 1, "self": 0.007842205000088143 }, "TrainerController.start_learning": { "total": 8397.117481523, "count": 1, "self": 6.113974659465384, "children": { "TrainerController._reset_env": { "total": 1.785357527004635, "count": 25, "self": 1.785357527004635 }, "TrainerController.advance": { "total": 8389.12927337553, "count": 341509, "self": 5.791082025740252, "children": { "env_step": { "total": 6568.530651061183, "count": 341509, "self": 4086.975086724873, "children": { "SubprocessEnvManager._take_step": { "total": 2478.029743193155, "count": 341509, "self": 37.83449738449144, "children": { "TorchPolicy.evaluate": { "total": 2440.1952458086635, "count": 629692, "self": 2440.1952458086635 } } }, "workers": { "total": 3.5258211431546442, "count": 341509, "self": 0.0, "children": { "worker_root": { "total": 8384.387879367789, "count": 341509, "is_parallel": true, "self": 4919.347502633706, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014395609987332136, "count": 2, "is_parallel": true, "self": 0.00035643999854073627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010831210001924774, "count": 8, "is_parallel": true, "self": 0.0010831210001924774 } } }, "UnityEnvironment.step": { "total": 0.018312120999325998, "count": 1, "is_parallel": true, "self": 0.00031302800016419496, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025231299969163956, "count": 1, "is_parallel": true, "self": 0.00025231299969163956 }, "communicator.exchange": { "total": 0.016696169000169903, "count": 1, "is_parallel": true, "self": 0.016696169000169903 }, "steps_from_proto": { "total": 0.001050610999300261, "count": 2, "is_parallel": true, "self": 0.00021824000032211188, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008323709989781491, "count": 8, "is_parallel": true, "self": 0.0008323709989781491 } } } } } } }, "UnityEnvironment.step": { "total": 3465.011589803081, "count": 341508, "is_parallel": true, "self": 126.96989602045869, "children": { "UnityEnvironment._generate_step_input": { "total": 80.706928390945, "count": 341508, "is_parallel": true, "self": 80.706928390945 }, "communicator.exchange": { "total": 2865.5826986206757, "count": 341508, "is_parallel": true, "self": 2865.5826986206757 }, "steps_from_proto": { "total": 391.7520667710014, "count": 683016, "is_parallel": true, "self": 76.85540863592814, "children": { "_process_rank_one_or_two_observation": { "total": 314.89665813507327, "count": 2732064, "is_parallel": true, "self": 314.89665813507327 } } } } }, "steps_from_proto": { "total": 0.028786931001377525, "count": 48, "is_parallel": true, "self": 0.005732883004384348, "children": { "_process_rank_one_or_two_observation": { "total": 0.023054047996993177, "count": 192, "is_parallel": true, "self": 0.023054047996993177 } } } } } } } } }, "trainer_advance": { "total": 1814.807540288608, "count": 341509, "self": 45.88860997628581, "children": { "process_trajectory": { "total": 921.7318699153202, "count": 341509, "self": 920.469845154319, "children": { "RLTrainer._checkpoint": { "total": 1.2620247610011575, "count": 10, "self": 1.2620247610011575 } } }, "_update_policy": { "total": 847.1870603970019, "count": 241, "self": 517.5609803069901, "children": { "TorchPOCAOptimizer.update": { "total": 329.6260800900118, "count": 7236, "self": 329.6260800900118 } } } } } } }, "trainer_threads": { "total": 6.320005923043936e-07, "count": 1, "self": 6.320005923043936e-07 }, "TrainerController._save_models": { "total": 0.088875329000075, "count": 1, "self": 0.0009119110000028741, "children": { "RLTrainer._checkpoint": { "total": 0.08796341800007212, "count": 1, "self": 0.08796341800007212 } } } } } } }