{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4084880352020264, "min": 1.4084880352020264, "max": 1.430176854133606, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69100.421875, "min": 68008.765625, "max": 77416.4375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.79553264604812, "min": 78.90220820189275, "max": 430.55172413793105, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48769.0, "min": 48769.0, "max": 50024.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999892.0, "min": 49904.0, "max": 1999892.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999892.0, "min": 49904.0, "max": 1999892.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4616518020629883, "min": 0.13863198459148407, "max": 2.470776081085205, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1432.681396484375, "min": 15.942678451538086, "max": 1528.669189453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8664396734991433, "min": 1.8865574733070705, "max": 3.9734972297209095, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2250.2678899765015, "min": 216.9541094303131, "max": 2344.6078567504883, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8664396734991433, "min": 1.8865574733070705, "max": 3.9734972297209095, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2250.2678899765015, "min": 216.9541094303131, "max": 2344.6078567504883, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016248468255273315, "min": 0.01284480686445022, "max": 0.019456996195690912, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04874540476581994, "min": 0.02568961372890044, "max": 0.058370988587072736, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.061369700771239065, "min": 0.022206527894983688, "max": 0.06480916049331427, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1841091023137172, "min": 0.044413055789967376, "max": 0.1841091023137172, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5401488199833277e-06, "min": 3.5401488199833277e-06, "max": 0.000295317826560725, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0620446459949983e-05, "min": 1.0620446459949983e-05, "max": 0.0008439414186861999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118001666666666, "min": 0.10118001666666666, "max": 0.19843927500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30354005, "min": 0.20750495000000002, "max": 0.5813138000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.888283166666659e-05, "min": 6.888283166666659e-05, "max": 0.0049221198224999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020664849499999976, "min": 0.00020664849499999976, "max": 0.01406755862, "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": "1675948209", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.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": "1675950537" }, "total": 2327.365509047, "count": 1, "self": 0.7379972109997652, "children": { "run_training.setup": { "total": 0.10857909400010612, "count": 1, "self": 0.10857909400010612 }, "TrainerController.start_learning": { "total": 2326.5189327420003, "count": 1, "self": 4.106991651091448, "children": { "TrainerController._reset_env": { "total": 10.697211121999999, "count": 1, "self": 10.697211121999999 }, "TrainerController.advance": { "total": 2311.537611729909, "count": 232550, "self": 4.506622485665957, "children": { "env_step": { "total": 1804.8569615360736, "count": 232550, "self": 1508.4482230351273, "children": { "SubprocessEnvManager._take_step": { "total": 293.73887384098566, "count": 232550, "self": 15.324721193002688, "children": { "TorchPolicy.evaluate": { "total": 278.414152647983, "count": 222892, "self": 69.68852854192664, "children": { "TorchPolicy.sample_actions": { "total": 208.72562410605633, "count": 222892, "self": 208.72562410605633 } } } } }, "workers": { "total": 2.6698646599606946, "count": 232550, "self": 0.0, "children": { "worker_root": { "total": 2318.0254101080054, "count": 232550, "is_parallel": true, "self": 1091.8492411169816, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018781359999593406, "count": 1, "is_parallel": true, "self": 0.00033357799998157134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015445579999777692, "count": 2, "is_parallel": true, "self": 0.0015445579999777692 } } }, "UnityEnvironment.step": { "total": 0.03025862300000881, "count": 1, "is_parallel": true, "self": 0.00030663199981972866, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020583400009854813, "count": 1, "is_parallel": true, "self": 0.00020583400009854813 }, "communicator.exchange": { "total": 0.028975012000046263, "count": 1, "is_parallel": true, "self": 0.028975012000046263 }, "steps_from_proto": { "total": 0.000771145000044271, "count": 1, "is_parallel": true, "self": 0.00023915799988571962, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005319870001585514, "count": 2, "is_parallel": true, "self": 0.0005319870001585514 } } } } } } }, "UnityEnvironment.step": { "total": 1226.1761689910238, "count": 232549, "is_parallel": true, "self": 37.61698352012331, "children": { "UnityEnvironment._generate_step_input": { "total": 77.3055818089615, "count": 232549, "is_parallel": true, "self": 77.3055818089615 }, "communicator.exchange": { "total": 1015.9780123749606, "count": 232549, "is_parallel": true, "self": 1015.9780123749606 }, "steps_from_proto": { "total": 95.2755912869784, "count": 232549, "is_parallel": true, "self": 36.833470299933424, "children": { "_process_rank_one_or_two_observation": { "total": 58.44212098704497, "count": 465098, "is_parallel": true, "self": 58.44212098704497 } } } } } } } } } } }, "trainer_advance": { "total": 502.174027708169, "count": 232550, "self": 6.364506100269637, "children": { "process_trajectory": { "total": 160.9200130899012, "count": 232550, "self": 159.51471948490052, "children": { "RLTrainer._checkpoint": { "total": 1.4052936050006792, "count": 10, "self": 1.4052936050006792 } } }, "_update_policy": { "total": 334.88950851799814, "count": 97, "self": 278.2426285399897, "children": { "TorchPPOOptimizer.update": { "total": 56.64687997800843, "count": 2910, "self": 56.64687997800843 } } } } } } }, "trainer_threads": { "total": 1.3720000424655154e-06, "count": 1, "self": 1.3720000424655154e-06 }, "TrainerController._save_models": { "total": 0.17711686700022256, "count": 1, "self": 0.002827371000421408, "children": { "RLTrainer._checkpoint": { "total": 0.17428949599980115, "count": 1, "self": 0.17428949599980115 } } } } } } }