{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4067463874816895, "min": 1.4066818952560425, "max": 1.4250901937484741, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69119.078125, "min": 67956.828125, "max": 78414.640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.23826714801444, "min": 79.6983870967742, "max": 383.64885496183206, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49438.0, "min": 48747.0, "max": 50258.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999908.0, "min": 49768.0, "max": 1999908.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999908.0, "min": 49768.0, "max": 1999908.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.45011043548584, "min": 0.08407046645879745, "max": 2.475292444229126, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1357.3612060546875, "min": 10.929161071777344, "max": 1489.8153076171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9208942172974885, "min": 1.552126714357963, "max": 3.986244498594259, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2172.1753963828087, "min": 201.7764728665352, "max": 2424.852175474167, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9208942172974885, "min": 1.552126714357963, "max": 3.986244498594259, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2172.1753963828087, "min": 201.7764728665352, "max": 2424.852175474167, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017940754758698555, "min": 0.013230316150778285, "max": 0.02143482902283722, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05382226427609567, "min": 0.02646063230155657, "max": 0.058624360933511824, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05528171579870913, "min": 0.02139717824757099, "max": 0.06283023785799742, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16584514739612738, "min": 0.04279435649514198, "max": 0.17778246613840262, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.660348779916653e-06, "min": 3.660348779916653e-06, "max": 0.00029531565156144996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.098104633974996e-05, "min": 1.098104633974996e-05, "max": 0.0008442847685717499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122008333333334, "min": 0.10122008333333334, "max": 0.19843855000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366025, "min": 0.20760354999999997, "max": 0.5814282500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.088215833333312e-05, "min": 7.088215833333312e-05, "max": 0.004922083644999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021264647499999936, "min": 0.00021264647499999936, "max": 0.014073269675, "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": "1673317084", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673319269" }, "total": 2184.114893613, "count": 1, "self": 0.4383435979998467, "children": { "run_training.setup": { "total": 0.10366796699997849, "count": 1, "self": 0.10366796699997849 }, "TrainerController.start_learning": { "total": 2183.572882048, "count": 1, "self": 3.6851324631224998, "children": { "TrainerController._reset_env": { "total": 7.356503326999928, "count": 1, "self": 7.356503326999928 }, "TrainerController.advance": { "total": 2172.414103940878, "count": 232451, "self": 3.8794662718773907, "children": { "env_step": { "total": 1703.783459850007, "count": 232451, "self": 1431.7397710310252, "children": { "SubprocessEnvManager._take_step": { "total": 269.5167887600312, "count": 232451, "self": 13.645575829948598, "children": { "TorchPolicy.evaluate": { "total": 255.8712129300826, "count": 222876, "self": 63.61287255311129, "children": { "TorchPolicy.sample_actions": { "total": 192.25834037697132, "count": 222876, "self": 192.25834037697132 } } } } }, "workers": { "total": 2.526900058950446, "count": 232451, "self": 0.0, "children": { "worker_root": { "total": 2175.98145138592, "count": 232451, "is_parallel": true, "self": 997.2372273919923, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001888448000045173, "count": 1, "is_parallel": true, "self": 0.0002879450000818906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016005029999632825, "count": 2, "is_parallel": true, "self": 0.0016005029999632825 } } }, "UnityEnvironment.step": { "total": 0.0355633649999163, "count": 1, "is_parallel": true, "self": 0.0002690950000214798, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001965619999282353, "count": 1, "is_parallel": true, "self": 0.0001965619999282353 }, "communicator.exchange": { "total": 0.03437573300004715, "count": 1, "is_parallel": true, "self": 0.03437573300004715 }, "steps_from_proto": { "total": 0.0007219749999194391, "count": 1, "is_parallel": true, "self": 0.00022780299991609354, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004941720000033456, "count": 2, "is_parallel": true, "self": 0.0004941720000033456 } } } } } } }, "UnityEnvironment.step": { "total": 1178.7442239939278, "count": 232450, "is_parallel": true, "self": 34.02461617604331, "children": { "UnityEnvironment._generate_step_input": { "total": 74.95942633700622, "count": 232450, "is_parallel": true, "self": 74.95942633700622 }, "communicator.exchange": { "total": 977.9082609170034, "count": 232450, "is_parallel": true, "self": 977.9082609170034 }, "steps_from_proto": { "total": 91.85192056387507, "count": 232450, "is_parallel": true, "self": 37.78099474273165, "children": { "_process_rank_one_or_two_observation": { "total": 54.07092582114342, "count": 464900, "is_parallel": true, "self": 54.07092582114342 } } } } } } } } } } }, "trainer_advance": { "total": 464.75117781899326, "count": 232451, "self": 5.744207535948135, "children": { "process_trajectory": { "total": 148.1589717850452, "count": 232451, "self": 147.01237237304588, "children": { "RLTrainer._checkpoint": { "total": 1.1465994119993184, "count": 10, "self": 1.1465994119993184 } } }, "_update_policy": { "total": 310.8479984979999, "count": 97, "self": 257.8009559909972, "children": { "TorchPPOOptimizer.update": { "total": 53.04704250700274, "count": 2910, "self": 53.04704250700274 } } } } } } }, "trainer_threads": { "total": 9.249997674487531e-07, "count": 1, "self": 9.249997674487531e-07 }, "TrainerController._save_models": { "total": 0.11714139200012141, "count": 1, "self": 0.0019894040001418034, "children": { "RLTrainer._checkpoint": { "total": 0.11515198799997961, "count": 1, "self": 0.11515198799997961 } } } } } } }