{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.295691967010498, "min": 3.295689344406128, "max": 3.295691967010498, "count": 2 }, "SoccerTwos.Policy.Entropy.sum": { "value": 105462.140625, "min": 105462.0625, "max": 105462.140625, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 905.625, "min": 885.75, "max": 905.625, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 28980.0, "min": 28344.0, "max": 28980.0, "count": 2 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1199.5057305918085, "min": 1199.2507195558546, "max": 1199.5057305918085, "count": 2 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4798.022922367234, "min": 2398.5014391117093, "max": 4798.022922367234, "count": 2 }, "SoccerTwos.Step.mean": { "value": 19694.0, "min": 9188.0, "max": 19694.0, "count": 2 }, "SoccerTwos.Step.sum": { "value": 19694.0, "min": 9188.0, "max": 19694.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07060559839010239, "min": -0.07060559839010239, "max": -0.07060343772172928, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.847267210483551, "min": -0.847267210483551, "max": -0.7766377925872803, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07060328871011734, "min": -0.07060345262289047, "max": -0.07060328871011734, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.8472394943237305, "min": -0.8472394943237305, "max": -0.7766379714012146, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10089999934037526, "min": -0.18181818181818182, "max": -0.10089999934037526, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.2107999920845032, "min": -2.0, "max": -1.2107999920845032, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10089999934037526, "min": -0.18181818181818182, "max": -0.10089999934037526, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.2107999920845032, "min": -2.0, "max": -1.2107999920845032, "count": 2 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675173173", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\simon\\Anaconda3\\envs\\rl2\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675173265" }, "total": 91.9008522, "count": 1, "self": 0.06464710000000196, "children": { "run_training.setup": { "total": 0.0912917000000002, "count": 1, "self": 0.0912917000000002 }, "TrainerController.start_learning": { "total": 91.7449134, "count": 1, "self": 0.07356070000012949, "children": { "TrainerController._reset_env": { "total": 4.1730279, "count": 1, "self": 4.1730279 }, "TrainerController.advance": { "total": 87.30454589999988, "count": 2004, "self": 0.05573020000009876, "children": { "env_step": { "total": 42.029193400000004, "count": 2004, "self": 33.07110630000009, "children": { "SubprocessEnvManager._take_step": { "total": 8.923475299999968, "count": 2004, "self": 0.37842490000002016, "children": { "TorchPolicy.evaluate": { "total": 8.545050399999948, "count": 4000, "self": 8.545050399999948 } } }, "workers": { "total": 0.0346117999999489, "count": 2004, "self": 0.0, "children": { "worker_root": { "total": 49.138396499999864, "count": 2004, "is_parallel": true, "self": 22.7424602999997, "children": { "steps_from_proto": { "total": 0.002005699999999777, "count": 2, "is_parallel": true, "self": 0.00038040000000094665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016252999999988305, "count": 8, "is_parallel": true, "self": 0.0016252999999988305 } } }, "UnityEnvironment.step": { "total": 26.393930500000167, "count": 2004, "is_parallel": true, "self": 1.3016270000001384, "children": { "UnityEnvironment._generate_step_input": { "total": 1.5905873999999809, "count": 2004, "is_parallel": true, "self": 1.5905873999999809 }, "communicator.exchange": { "total": 18.730602399999967, "count": 2004, "is_parallel": true, "self": 18.730602399999967 }, "steps_from_proto": { "total": 4.77111370000008, "count": 4008, "is_parallel": true, "self": 0.9033070000000754, "children": { "_process_rank_one_or_two_observation": { "total": 3.8678067000000045, "count": 16032, "is_parallel": true, "self": 3.8678067000000045 } } } } } } } } } } }, "trainer_advance": { "total": 45.21962229999978, "count": 2004, "self": 0.25743169999990556, "children": { "process_trajectory": { "total": 10.384502399999864, "count": 2004, "self": 10.384502399999864 }, "_update_policy": { "total": 34.577688200000004, "count": 1, "self": 4.725579899999985, "children": { "TorchPOCAOptimizer.update": { "total": 29.85210830000002, "count": 19, "self": 29.85210830000002 } } } } } } }, "trainer_threads": { "total": 2.3999999996249244e-06, "count": 1, "self": 2.3999999996249244e-06 }, "TrainerController._save_models": { "total": 0.19377649999999846, "count": 1, "self": 0.0029433000000125276, "children": { "RLTrainer._checkpoint": { "total": 0.19083319999998594, "count": 1, "self": 0.19083319999998594 } } } } } } }