{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4026494026184082, "min": 1.4026494026184082, "max": 1.4272713661193848, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70978.265625, "min": 68758.8671875, "max": 78664.953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.61986301369863, "min": 83.82462057335582, "max": 384.48091603053433, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49418.0, "min": 49129.0, "max": 50367.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49748.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49748.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3710224628448486, "min": 0.051666051149368286, "max": 2.452930212020874, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1384.6771240234375, "min": 6.716586589813232, "max": 1435.35888671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6579249703312575, "min": 1.8194147303700448, "max": 3.9259893586623527, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2136.2281826734543, "min": 236.5239149481058, "max": 2328.111689686775, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6579249703312575, "min": 1.8194147303700448, "max": 3.9259893586623527, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2136.2281826734543, "min": 236.5239149481058, "max": 2328.111689686775, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01803078762928231, "min": 0.01419157469451117, "max": 0.021592735803763693, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.054092362887846926, "min": 0.02838314938902234, "max": 0.056129414393399205, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05417680959734652, "min": 0.023246020389099918, "max": 0.061953774177365833, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16253042879203955, "min": 0.046492040778199836, "max": 0.1858613225320975, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.421748859450009e-06, "min": 3.421748859450009e-06, "max": 0.00029535135154955, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0265246578350026e-05, "min": 1.0265246578350026e-05, "max": 0.00084429706856765, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114055, "min": 0.10114055, "max": 0.19845045000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30342165, "min": 0.20741350000000008, "max": 0.58143235, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.691344500000016e-05, "min": 6.691344500000016e-05, "max": 0.004922677455, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020074033500000048, "min": 0.00020074033500000048, "max": 0.014073474264999997, "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": "1677072245", "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": "1677074696" }, "total": 2450.928094976, "count": 1, "self": 0.437480510000114, "children": { "run_training.setup": { "total": 0.1171684670000559, "count": 1, "self": 0.1171684670000559 }, "TrainerController.start_learning": { "total": 2450.373445999, "count": 1, "self": 4.636089918984453, "children": { "TrainerController._reset_env": { "total": 10.563923882999916, "count": 1, "self": 10.563923882999916 }, "TrainerController.advance": { "total": 2435.0598067010155, "count": 232212, "self": 4.973974776872183, "children": { "env_step": { "total": 1907.522884557066, "count": 232212, "self": 1590.620015143071, "children": { "SubprocessEnvManager._take_step": { "total": 314.0034171329795, "count": 232212, "self": 16.4659212199374, "children": { "TorchPolicy.evaluate": { "total": 297.5374959130421, "count": 222980, "self": 73.39676506896683, "children": { "TorchPolicy.sample_actions": { "total": 224.14073084407528, "count": 222980, "self": 224.14073084407528 } } } } }, "workers": { "total": 2.899452281015442, "count": 232212, "self": 0.0, "children": { "worker_root": { "total": 2442.0112828779497, "count": 232212, "is_parallel": true, "self": 1150.9650530869114, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002256392999925083, "count": 1, "is_parallel": true, "self": 0.0003967830000419781, "children": { "_process_rank_one_or_two_observation": { "total": 0.001859609999883105, "count": 2, "is_parallel": true, "self": 0.001859609999883105 } } }, "UnityEnvironment.step": { "total": 0.03179081500002212, "count": 1, "is_parallel": true, "self": 0.00033575000009022915, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021701299999676849, "count": 1, "is_parallel": true, "self": 0.00021701299999676849 }, "communicator.exchange": { "total": 0.030456364999963625, "count": 1, "is_parallel": true, "self": 0.030456364999963625 }, "steps_from_proto": { "total": 0.0007816869999714982, "count": 1, "is_parallel": true, "self": 0.0002796070000385953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005020799999329029, "count": 2, "is_parallel": true, "self": 0.0005020799999329029 } } } } } } }, "UnityEnvironment.step": { "total": 1291.0462297910383, "count": 232211, "is_parallel": true, "self": 38.17835343186766, "children": { "UnityEnvironment._generate_step_input": { "total": 83.05885413602482, "count": 232211, "is_parallel": true, "self": 83.05885413602482 }, "communicator.exchange": { "total": 1070.7461917670325, "count": 232211, "is_parallel": true, "self": 1070.7461917670325 }, "steps_from_proto": { "total": 99.06283045611337, "count": 232211, "is_parallel": true, "self": 40.48108953709891, "children": { "_process_rank_one_or_two_observation": { "total": 58.581740919014464, "count": 464422, "is_parallel": true, "self": 58.581740919014464 } } } } } } } } } } }, "trainer_advance": { "total": 522.5629473670775, "count": 232212, "self": 6.79390180011967, "children": { "process_trajectory": { "total": 171.0187851979598, "count": 232212, "self": 169.73317456996028, "children": { "RLTrainer._checkpoint": { "total": 1.2856106279995174, "count": 10, "self": 1.2856106279995174 } } }, "_update_policy": { "total": 344.75026036899806, "count": 97, "self": 287.2776024819897, "children": { "TorchPPOOptimizer.update": { "total": 57.47265788700838, "count": 2910, "self": 57.47265788700838 } } } } } } }, "trainer_threads": { "total": 9.140003385255113e-07, "count": 1, "self": 9.140003385255113e-07 }, "TrainerController._save_models": { "total": 0.11362458199982939, "count": 1, "self": 0.002109075000134908, "children": { "RLTrainer._checkpoint": { "total": 0.11151550699969448, "count": 1, "self": 0.11151550699969448 } } } } } } }