{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4037076234817505, "min": 1.4037076234817505, "max": 1.4272019863128662, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71030.4140625, "min": 68093.15625, "max": 77894.6953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.98710865561694, "min": 74.23493975903614, "max": 405.44354838709677, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49406.0, "min": 48957.0, "max": 50275.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999984.0, "min": 49649.0, "max": 1999984.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999984.0, "min": 49649.0, "max": 1999984.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.474163293838501, "min": 0.1513908952474594, "max": 2.5314581394195557, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1343.470703125, "min": 18.62108039855957, "max": 1637.406982421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.724499191039175, "min": 1.8183182918928502, "max": 4.022179588052621, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2022.403060734272, "min": 223.6531499028206, "max": 2601.2837501764297, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.724499191039175, "min": 1.8183182918928502, "max": 4.022179588052621, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2022.403060734272, "min": 223.6531499028206, "max": 2601.2837501764297, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018350951917657062, "min": 0.012894646848568905, "max": 0.01945003500004532, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05505285575297118, "min": 0.02578929369713781, "max": 0.05835010500013595, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05378823292752107, "min": 0.021816426422446966, "max": 0.06438655277921095, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1613646987825632, "min": 0.04363285284489393, "max": 0.19315965833763282, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.561348812916661e-06, "min": 3.561348812916661e-06, "max": 0.0002953170015609999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0684046438749982e-05, "min": 1.0684046438749982e-05, "max": 0.0008438349187217001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118708333333337, "min": 0.10118708333333337, "max": 0.19843900000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035612500000001, "min": 0.20753539999999998, "max": 0.5812783000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.923545833333325e-05, "min": 6.923545833333325e-05, "max": 0.0049221061, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020770637499999974, "min": 0.00020770637499999974, "max": 0.014065787169999998, "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": "1699872381", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699874793" }, "total": 2411.7095970299997, "count": 1, "self": 0.6281567390001328, "children": { "run_training.setup": { "total": 0.04380504299999188, "count": 1, "self": 0.04380504299999188 }, "TrainerController.start_learning": { "total": 2411.037635248, "count": 1, "self": 4.6696301149436295, "children": { "TrainerController._reset_env": { "total": 8.27093262699998, "count": 1, "self": 8.27093262699998 }, "TrainerController.advance": { "total": 2397.9472879920563, "count": 233263, "self": 4.677474523070487, "children": { "env_step": { "total": 1898.6983415269679, "count": 233263, "self": 1567.851466259915, "children": { "SubprocessEnvManager._take_step": { "total": 328.00815839106417, "count": 233263, "self": 16.44616067002346, "children": { "TorchPolicy.evaluate": { "total": 311.5619977210407, "count": 223085, "self": 311.5619977210407 } } }, "workers": { "total": 2.8387168759886094, "count": 233263, "self": 0.0, "children": { "worker_root": { "total": 2403.470084203052, "count": 233263, "is_parallel": true, "self": 1128.1687460280755, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008007540000107838, "count": 1, "is_parallel": true, "self": 0.0002303790000155459, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005703749999952379, "count": 2, "is_parallel": true, "self": 0.0005703749999952379 } } }, "UnityEnvironment.step": { "total": 0.03379089200001317, "count": 1, "is_parallel": true, "self": 0.000283657000011317, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002029180000135966, "count": 1, "is_parallel": true, "self": 0.0002029180000135966 }, "communicator.exchange": { "total": 0.03260610999998903, "count": 1, "is_parallel": true, "self": 0.03260610999998903 }, "steps_from_proto": { "total": 0.0006982069999992291, "count": 1, "is_parallel": true, "self": 0.00018022000000428307, "children": { "_process_rank_one_or_two_observation": { "total": 0.000517986999994946, "count": 2, "is_parallel": true, "self": 0.000517986999994946 } } } } } } }, "UnityEnvironment.step": { "total": 1275.3013381749765, "count": 233262, "is_parallel": true, "self": 40.117128136796055, "children": { "UnityEnvironment._generate_step_input": { "total": 83.51254767007356, "count": 233262, "is_parallel": true, "self": 83.51254767007356 }, "communicator.exchange": { "total": 1062.499721082069, "count": 233262, "is_parallel": true, "self": 1062.499721082069 }, "steps_from_proto": { "total": 89.17194128603799, "count": 233262, "is_parallel": true, "self": 31.27153670499999, "children": { "_process_rank_one_or_two_observation": { "total": 57.900404581038, "count": 466524, "is_parallel": true, "self": 57.900404581038 } } } } } } } } } } }, "trainer_advance": { "total": 494.5714719420181, "count": 233263, "self": 6.401244994990293, "children": { "process_trajectory": { "total": 151.76085942302848, "count": 233263, "self": 150.6125492690282, "children": { "RLTrainer._checkpoint": { "total": 1.148310154000285, "count": 10, "self": 1.148310154000285 } } }, "_update_policy": { "total": 336.4093675239993, "count": 97, "self": 274.45914325999445, "children": { "TorchPPOOptimizer.update": { "total": 61.95022426400487, "count": 2910, "self": 61.95022426400487 } } } } } } }, "trainer_threads": { "total": 1.2430000424501486e-06, "count": 1, "self": 1.2430000424501486e-06 }, "TrainerController._save_models": { "total": 0.14978327099970556, "count": 1, "self": 0.002498766999451618, "children": { "RLTrainer._checkpoint": { "total": 0.14728450400025395, "count": 1, "self": 0.14728450400025395 } } } } } } }