{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4101561307907104, "min": 1.4101561307907104, "max": 1.4297873973846436, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71125.453125, "min": 69220.7265625, "max": 77510.5859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 114.64434180138568, "min": 98.26, "max": 377.82706766917295, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49641.0, "min": 48817.0, "max": 50251.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999978.0, "min": 49969.0, "max": 1999978.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999978.0, "min": 49969.0, "max": 1999978.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.298859119415283, "min": 0.16875991225242615, "max": 2.395397663116455, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 995.406005859375, "min": 22.276308059692383, "max": 1157.035888671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.569543497391716, "min": 1.8062444026723052, "max": 3.843284548885206, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1545.612334370613, "min": 238.4242611527443, "max": 1830.4866644740105, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.569543497391716, "min": 1.8062444026723052, "max": 3.843284548885206, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1545.612334370613, "min": 238.4242611527443, "max": 1830.4866644740105, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01768509768622203, "min": 0.01362849017249472, "max": 0.019018190774174097, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05305529305866609, "min": 0.02823617329316524, "max": 0.055038205950404526, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04508210902826654, "min": 0.020912286328772706, "max": 0.05848990107576052, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1352463270847996, "min": 0.04182457265754541, "max": 0.16124623951812583, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3304488898833365e-06, "min": 3.3304488898833365e-06, "max": 0.0002953596765467749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.991346669650009e-06, "min": 9.991346669650009e-06, "max": 0.0008443305185564998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011101166666667, "min": 0.1011101166666667, "max": 0.19845322500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033303500000001, "min": 0.2073747, "max": 0.5814435, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.539482166666672e-05, "min": 6.539482166666672e-05, "max": 0.004922815927500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019618446500000017, "min": 0.00019618446500000017, "max": 0.01407403065, "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": "1677006430", "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": "1677008782" }, "total": 2352.466358191, "count": 1, "self": 0.4407137270000021, "children": { "run_training.setup": { "total": 0.17226435899999615, "count": 1, "self": 0.17226435899999615 }, "TrainerController.start_learning": { "total": 2351.853380105, "count": 1, "self": 4.148345409998001, "children": { "TrainerController._reset_env": { "total": 9.694891082000026, "count": 1, "self": 9.694891082000026 }, "TrainerController.advance": { "total": 2337.862091373002, "count": 231195, "self": 4.340767764937482, "children": { "env_step": { "total": 1823.964278198015, "count": 231195, "self": 1519.9592986221157, "children": { "SubprocessEnvManager._take_step": { "total": 301.3181223689264, "count": 231195, "self": 15.380059058968868, "children": { "TorchPolicy.evaluate": { "total": 285.93806330995756, "count": 223002, "self": 70.97591998690166, "children": { "TorchPolicy.sample_actions": { "total": 214.9621433230559, "count": 223002, "self": 214.9621433230559 } } } } }, "workers": { "total": 2.6868572069729453, "count": 231195, "self": 0.0, "children": { "worker_root": { "total": 2343.506623644007, "count": 231195, "is_parallel": true, "self": 1109.6434265829816, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020055769999771655, "count": 1, "is_parallel": true, "self": 0.0003935259999252594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016120510000519062, "count": 2, "is_parallel": true, "self": 0.0016120510000519062 } } }, "UnityEnvironment.step": { "total": 0.028567115999976522, "count": 1, "is_parallel": true, "self": 0.0003042449998247321, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002053300000852687, "count": 1, "is_parallel": true, "self": 0.0002053300000852687 }, "communicator.exchange": { "total": 0.027141887000084353, "count": 1, "is_parallel": true, "self": 0.027141887000084353 }, "steps_from_proto": { "total": 0.0009156539999821689, "count": 1, "is_parallel": true, "self": 0.00045830199996999, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004573520000121789, "count": 2, "is_parallel": true, "self": 0.0004573520000121789 } } } } } } }, "UnityEnvironment.step": { "total": 1233.8631970610254, "count": 231194, "is_parallel": true, "self": 38.250821425020604, "children": { "UnityEnvironment._generate_step_input": { "total": 77.7146225660066, "count": 231194, "is_parallel": true, "self": 77.7146225660066 }, "communicator.exchange": { "total": 1026.8972236139375, "count": 231194, "is_parallel": true, "self": 1026.8972236139375 }, "steps_from_proto": { "total": 91.00052945606046, "count": 231194, "is_parallel": true, "self": 37.022380472972486, "children": { "_process_rank_one_or_two_observation": { "total": 53.978148983087976, "count": 462388, "is_parallel": true, "self": 53.978148983087976 } } } } } } } } } } }, "trainer_advance": { "total": 509.55704541004945, "count": 231195, "self": 6.5725614040463824, "children": { "process_trajectory": { "total": 155.70133451000152, "count": 231195, "self": 154.4082593820017, "children": { "RLTrainer._checkpoint": { "total": 1.2930751279998276, "count": 10, "self": 1.2930751279998276 } } }, "_update_policy": { "total": 347.28314949600156, "count": 97, "self": 289.66598250900574, "children": { "TorchPPOOptimizer.update": { "total": 57.61716698699581, "count": 2910, "self": 57.61716698699581 } } } } } } }, "trainer_threads": { "total": 8.809997780190315e-07, "count": 1, "self": 8.809997780190315e-07 }, "TrainerController._save_models": { "total": 0.14805135899996458, "count": 1, "self": 0.0022460189998128044, "children": { "RLTrainer._checkpoint": { "total": 0.14580534000015177, "count": 1, "self": 0.14580534000015177 } } } } } } }