{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4963933229446411, "min": 1.408483624458313, "max": 3.29571270942688, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29353.251953125, "min": 17898.99609375, "max": 129690.0234375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.85526315789474, "min": 48.93, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19716.0, "min": 16320.0, "max": 23548.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1986.2290766666756, "min": 1196.4713145206497, "max": 2035.545787867456, "count": 4718 }, "SoccerTwos.Self-play.ELO.sum": { "value": 301906.8196533347, "min": 2395.5018840418998, "max": 389188.2794481589, "count": 4718 }, "SoccerTwos.Step.mean": { "value": 49999988.0, "min": 9760.0, "max": 49999988.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999988.0, "min": 9760.0, "max": 49999988.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01866314746439457, "min": -0.14000248908996582, "max": 0.12597665190696716, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.8367984294891357, "min": -22.540401458740234, "max": 16.092144012451172, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.018723903223872185, "min": -0.14310425519943237, "max": 0.1285843402147293, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.8460333347320557, "min": -22.094587326049805, "max": 16.1998348236084, "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": -0.03278157899254247, "min": -0.6470588235294118, "max": 0.5818533301353455, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.982800006866455, "min": -62.61580002307892, "max": 53.87600004673004, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03278157899254247, "min": -0.6470588235294118, "max": 0.5818533301353455, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.982800006866455, "min": -62.61580002307892, "max": 53.87600004673004, "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": 0.01672766050323844, "min": 0.010218130899981285, "max": 0.026053640067887802, "count": 2409 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01672766050323844, "min": 0.010218130899981285, "max": 0.026053640067887802, "count": 2409 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10420755222439766, "min": 2.20016370307737e-09, "max": 0.10751013110081355, "count": 2409 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10420755222439766, "min": 2.20016370307737e-09, "max": 0.10751013110081355, "count": 2409 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10512582957744598, "min": 2.462296692466263e-09, "max": 0.1082919495801131, "count": 2409 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10512582957744598, "min": 2.462296692466263e-09, "max": 0.1082919495801131, "count": 2409 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2409 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2409 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2409 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2409 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2409 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2409 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676069006", "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/ivanchistyakov/Desktop/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --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": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1676391259" }, "total": 322242.644030672, "count": 1, "self": 0.3279518609633669, "children": { "run_training.setup": { "total": 0.016999580000000014, "count": 1, "self": 0.016999580000000014 }, "TrainerController.start_learning": { "total": 322242.299079231, "count": 1, "self": 59.97265928611159, "children": { "TrainerController._reset_env": { "total": 6.2347968669171685, "count": 250, "self": 6.2347968669171685 }, "TrainerController.advance": { "total": 322175.92392550997, "count": 3376647, "self": 63.354187416203786, "children": { "env_step": { "total": 42838.97478724331, "count": 3376647, "self": 34941.08387098866, "children": { "SubprocessEnvManager._take_step": { "total": 7858.295024526432, "count": 3376647, "self": 333.92455918631913, "children": { "TorchPolicy.evaluate": { "total": 7524.370465340113, "count": 6305168, "self": 7524.370465340113 } } }, "workers": { "total": 39.59589172821464, "count": 3376647, "self": 0.0, "children": { "worker_root": { "total": 322142.54228148673, "count": 3376647, "is_parallel": true, "self": 294074.76907246886, "children": { "steps_from_proto": { "total": 0.3860330660266218, "count": 500, "is_parallel": true, "self": 0.0781055047419148, "children": { "_process_rank_one_or_two_observation": { "total": 0.307927561284707, "count": 2000, "is_parallel": true, "self": 0.307927561284707 } } }, "UnityEnvironment.step": { "total": 28067.38717595182, "count": 3376647, "is_parallel": true, "self": 1689.5224428774309, "children": { "UnityEnvironment._generate_step_input": { "total": 1064.3330249926516, "count": 3376647, "is_parallel": true, "self": 1064.3330249926516 }, "communicator.exchange": { "total": 20361.388769087243, "count": 3376647, "is_parallel": true, "self": 20361.388769087243 }, "steps_from_proto": { "total": 4952.142938994494, "count": 6753294, "is_parallel": true, "self": 1010.4682478903151, "children": { "_process_rank_one_or_two_observation": { "total": 3941.674691104179, "count": 27013176, "is_parallel": true, "self": 3941.674691104179 } } } } } } } } } } }, "trainer_advance": { "total": 279273.5949508505, "count": 3376647, "self": 435.3135163091356, "children": { "process_trajectory": { "total": 12910.544843309937, "count": 3376647, "self": 12890.749638091116, "children": { "RLTrainer._checkpoint": { "total": 19.79520521882091, "count": 100, "self": 19.79520521882091 } } }, "_update_policy": { "total": 265927.73659123137, "count": 2409, "self": 6506.972498562565, "children": { "TorchPOCAOptimizer.update": { "total": 259420.7640926688, "count": 72270, "self": 259420.7640926688 } } } } } } }, "trainer_threads": { "total": 7.500057108700275e-07, "count": 1, "self": 7.500057108700275e-07 }, "TrainerController._save_models": { "total": 0.16769681801088154, "count": 1, "self": 0.0011068930034525692, "children": { "RLTrainer._checkpoint": { "total": 0.16658992500742897, "count": 1, "self": 0.16658992500742897 } } } } } } }