{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.183039903640747, "min": 2.880762815475464, "max": 3.29575514793396, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 76189.2421875, "min": 20737.91796875, "max": 127593.078125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 430.45454545454544, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 15284.0, "max": 26268.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.8167751293045, "min": 1179.8928992673655, "max": 1199.2235985323605, "count": 275 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2383.633550258609, "min": 2359.785798534731, "max": 21474.00064186151, "count": 275 }, "SoccerTwos.Step.mean": { "value": 4999344.0, "min": 9152.0, "max": 4999344.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999344.0, "min": 9152.0, "max": 4999344.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0013104419922456145, "min": -0.15900614857673645, "max": 0.042225565761327744, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.013104420155286789, "min": -1.7602508068084717, "max": 0.5911579132080078, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0012099891901016235, "min": -0.15580807626247406, "max": 0.04227247089147568, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.012099891901016235, "min": -1.757559895515442, "max": 0.5918145775794983, "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": 0.0, "min": -0.6666666666666666, "max": 0.2967999998260947, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.585999965667725, "max": 5.04559999704361, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6666666666666666, "max": 0.2967999998260947, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.585999965667725, "max": 5.04559999704361, "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": 0.01538998297182843, "min": 0.011353943989767383, "max": 0.022224253253079952, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01538998297182843, "min": 0.011353943989767383, "max": 0.022224253253079952, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.000749148068522724, "min": 7.7705520980705e-09, "max": 0.015162438420035566, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.000749148068522724, "min": 7.7705520980705e-09, "max": 0.015162438420035566, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0007507226361970728, "min": 9.176770691491736e-09, "max": 0.01584275833738502, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0007507226361970728, "min": 9.176770691491736e-09, "max": 0.01584275833738502, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742152696", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/bale/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env ./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1742220600" }, "total": 67901.82784771896, "count": 1, "self": 1.045206509064883, "children": { "run_training.setup": { "total": 0.5197419680189341, "count": 1, "self": 0.5197419680189341 }, "TrainerController.start_learning": { "total": 67900.26289924188, "count": 1, "self": 10.32548879343085, "children": { "TrainerController._reset_env": { "total": 15.308325024787337, "count": 25, "self": 15.308325024787337 }, "TrainerController.advance": { "total": 67874.29187158658, "count": 325310, "self": 10.567703283391893, "children": { "env_step": { "total": 51792.13490111055, "count": 325310, "self": 49851.33882967639, "children": { "SubprocessEnvManager._take_step": { "total": 1934.3037551918533, "count": 325310, "self": 74.57425758964382, "children": { "TorchPolicy.evaluate": { "total": 1859.7294976022094, "count": 646002, "self": 1859.7294976022094 } } }, "workers": { "total": 6.4923162423074245, "count": 325310, "self": 0.0, "children": { "worker_root": { "total": 67864.11189677683, "count": 325310, "is_parallel": true, "self": 19329.57389694592, "children": { "steps_from_proto": { "total": 0.10252807033248246, "count": 50, "is_parallel": true, "self": 0.017276315949857235, "children": { "_process_rank_one_or_two_observation": { "total": 0.08525175438262522, "count": 200, "is_parallel": true, "self": 0.08525175438262522 } } }, "UnityEnvironment.step": { "total": 48534.435471760575, "count": 325310, "is_parallel": true, "self": 165.93206412019208, "children": { "UnityEnvironment._generate_step_input": { "total": 927.1571539014112, "count": 325310, "is_parallel": true, "self": 927.1571539014112 }, "communicator.exchange": { "total": 45718.21709376387, "count": 325310, "is_parallel": true, "self": 45718.21709376387 }, "steps_from_proto": { "total": 1723.1291599750984, "count": 650620, "is_parallel": true, "self": 239.90544259059243, "children": { "_process_rank_one_or_two_observation": { "total": 1483.223717384506, "count": 2602480, "is_parallel": true, "self": 1483.223717384506 } } } } } } } } } } }, "trainer_advance": { "total": 16071.589267192641, "count": 325310, "self": 89.06779530528001, "children": { "process_trajectory": { "total": 1790.4417970674112, "count": 325310, "self": 1785.6133967086207, "children": { "RLTrainer._checkpoint": { "total": 4.828400358790532, "count": 10, "self": 4.828400358790532 } } }, "_update_policy": { "total": 14192.07967481995, "count": 231, "self": 982.8635043660179, "children": { "TorchPOCAOptimizer.update": { "total": 13209.216170453932, "count": 6930, "self": 13209.216170453932 } } } } } } }, "trainer_threads": { "total": 1.7720740288496017e-06, "count": 1, "self": 1.7720740288496017e-06 }, "TrainerController._save_models": { "total": 0.33721206500194967, "count": 1, "self": 0.005977702792733908, "children": { "RLTrainer._checkpoint": { "total": 0.33123436220921576, "count": 1, "self": 0.33123436220921576 } } } } } } }