{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4026539325714111, "min": 1.4026539325714111, "max": 1.4271001815795898, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72796.3359375, "min": 68440.1328125, "max": 75295.9375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.62544802867383, "min": 85.41450777202073, "max": 392.7165354330709, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49453.0, "min": 48812.0, "max": 50151.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999978.0, "min": 49717.0, "max": 1999978.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999978.0, "min": 49717.0, "max": 1999978.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4153366088867188, "min": 0.11018379032611847, "max": 2.452255964279175, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1347.7578125, "min": 13.883157730102539, "max": 1385.859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8054383872444055, "min": 1.8134398484040821, "max": 3.969387557566166, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2123.4346200823784, "min": 228.49342089891434, "max": 2200.4454111754894, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8054383872444055, "min": 1.8134398484040821, "max": 3.969387557566166, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2123.4346200823784, "min": 228.49342089891434, "max": 2200.4454111754894, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017255277412025153, "min": 0.012659564206599801, "max": 0.019972265213436913, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05176583223607546, "min": 0.025319128413199603, "max": 0.05621289710012055, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05802199823988808, "min": 0.021334158380826314, "max": 0.06411152326812347, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17406599471966425, "min": 0.04266831676165263, "max": 0.1886691339313984, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3839488720499984e-06, "min": 3.3839488720499984e-06, "max": 0.0002953195515601499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0151846616149995e-05, "min": 1.0151846616149995e-05, "max": 0.0008441148186283999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112795000000002, "min": 0.10112795000000002, "max": 0.19843984999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30338385000000007, "min": 0.2073868, "max": 0.5813716, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.628470500000002e-05, "min": 6.628470500000002e-05, "max": 0.004922148515, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019885411500000007, "min": 0.00019885411500000007, "max": 0.01407044284, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695726637", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695729308" }, "total": 2671.4244914479996, "count": 1, "self": 0.6812937009999587, "children": { "run_training.setup": { "total": 0.06395743000030052, "count": 1, "self": 0.06395743000030052 }, "TrainerController.start_learning": { "total": 2670.6792403169993, "count": 1, "self": 4.861073592003777, "children": { "TrainerController._reset_env": { "total": 5.521811214999616, "count": 1, "self": 5.521811214999616 }, "TrainerController.advance": { "total": 2660.081936982996, "count": 232316, "self": 5.1222568991506705, "children": { "env_step": { "total": 2086.9129256459, "count": 232316, "self": 1762.1324723373273, "children": { "SubprocessEnvManager._take_step": { "total": 321.48291669783885, "count": 232316, "self": 18.676123742506206, "children": { "TorchPolicy.evaluate": { "total": 302.80679295533264, "count": 223096, "self": 302.80679295533264 } } }, "workers": { "total": 3.297536610733914, "count": 232316, "self": 0.0, "children": { "worker_root": { "total": 2662.2236385515007, "count": 232316, "is_parallel": true, "self": 1228.547570718304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001097968999602017, "count": 1, "is_parallel": true, "self": 0.00034464799864508677, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007533210009569302, "count": 2, "is_parallel": true, "self": 0.0007533210009569302 } } }, "UnityEnvironment.step": { "total": 0.03489214099954552, "count": 1, "is_parallel": true, "self": 0.00048728899946581805, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002548180000303546, "count": 1, "is_parallel": true, "self": 0.0002548180000303546 }, "communicator.exchange": { "total": 0.0330818200000067, "count": 1, "is_parallel": true, "self": 0.0330818200000067 }, "steps_from_proto": { "total": 0.0010682140000426443, "count": 1, "is_parallel": true, "self": 0.0003308019995529321, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007374120004897122, "count": 2, "is_parallel": true, "self": 0.0007374120004897122 } } } } } } }, "UnityEnvironment.step": { "total": 1433.6760678331966, "count": 232315, "is_parallel": true, "self": 42.571516131572025, "children": { "UnityEnvironment._generate_step_input": { "total": 88.70938974992987, "count": 232315, "is_parallel": true, "self": 88.70938974992987 }, "communicator.exchange": { "total": 1195.005726561778, "count": 232315, "is_parallel": true, "self": 1195.005726561778 }, "steps_from_proto": { "total": 107.3894353899168, "count": 232315, "is_parallel": true, "self": 40.63081208319909, "children": { "_process_rank_one_or_two_observation": { "total": 66.75862330671771, "count": 464630, "is_parallel": true, "self": 66.75862330671771 } } } } } } } } } } }, "trainer_advance": { "total": 568.0467544379453, "count": 232316, "self": 7.398737340887237, "children": { "process_trajectory": { "total": 152.87929067305595, "count": 232316, "self": 151.3961391470557, "children": { "RLTrainer._checkpoint": { "total": 1.4831515260002561, "count": 10, "self": 1.4831515260002561 } } }, "_update_policy": { "total": 407.7687264240021, "count": 97, "self": 347.8189020439995, "children": { "TorchPPOOptimizer.update": { "total": 59.94982438000261, "count": 2910, "self": 59.94982438000261 } } } } } } }, "trainer_threads": { "total": 1.8580003597890027e-06, "count": 1, "self": 1.8580003597890027e-06 }, "TrainerController._save_models": { "total": 0.21441666899954726, "count": 1, "self": 0.0029297559995029587, "children": { "RLTrainer._checkpoint": { "total": 0.2114869130000443, "count": 1, "self": 0.2114869130000443 } } } } } } }