{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406927227973938, "min": 1.406927227973938, "max": 1.428769826889038, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70018.546875, "min": 68220.6328125, "max": 77445.8515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 132.872, "min": 91.06998158379373, "max": 384.6793893129771, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49827.0, "min": 48938.0, "max": 50393.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999613.0, "min": 49955.0, "max": 1999613.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999613.0, "min": 49955.0, "max": 1999613.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2671597003936768, "min": 0.15929746627807617, "max": 2.384432315826416, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 852.4520263671875, "min": 20.70867156982422, "max": 1233.52685546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.3908320108943797, "min": 1.7909623205661773, "max": 3.8640098866209924, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1274.9528360962868, "min": 232.82510167360306, "max": 2009.7998051643372, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.3908320108943797, "min": 1.7909623205661773, "max": 3.8640098866209924, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1274.9528360962868, "min": 232.82510167360306, "max": 2009.7998051643372, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0132809779414553, "min": 0.0132809779414553, "max": 0.020505904977108004, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0265619558829106, "min": 0.0265619558829106, "max": 0.060299617767062344, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.038285991673668224, "min": 0.020951938225577275, "max": 0.06354543711576197, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.07657198334733645, "min": 0.04190387645115455, "max": 0.1906363113472859, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.408673530474999e-06, "min": 4.408673530474999e-06, "max": 0.00029535052654982495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.817347060949999e-06, "min": 8.817347060949999e-06, "max": 0.0008443404185532, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101469525, "min": 0.101469525, "max": 0.198450175, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20293905, "min": 0.20293905, "max": 0.5814468000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.332929749999996e-05, "min": 8.332929749999996e-05, "max": 0.0049226637325, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016665859499999993, "min": 0.00016665859499999993, "max": 0.014074195320000003, "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": "1687047273", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687049597" }, "total": 2324.435963293, "count": 1, "self": 0.5977025989996037, "children": { "run_training.setup": { "total": 0.04172141899999815, "count": 1, "self": 0.04172141899999815 }, "TrainerController.start_learning": { "total": 2323.796539275, "count": 1, "self": 4.065421892948052, "children": { "TrainerController._reset_env": { "total": 4.269979696999997, "count": 1, "self": 4.269979696999997 }, "TrainerController.advance": { "total": 2315.266302218052, "count": 231458, "self": 4.321952933211833, "children": { "env_step": { "total": 1809.9517668070112, "count": 231458, "self": 1528.044112137777, "children": { "SubprocessEnvManager._take_step": { "total": 279.13139678622474, "count": 231458, "self": 16.439107199272996, "children": { "TorchPolicy.evaluate": { "total": 262.69228958695174, "count": 223100, "self": 262.69228958695174 } } }, "workers": { "total": 2.776257883009521, "count": 231458, "self": 0.0, "children": { "worker_root": { "total": 2316.0948341398284, "count": 231458, "is_parallel": true, "self": 1065.3243277448305, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010407820000182255, "count": 1, "is_parallel": true, "self": 0.00027034100003220374, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007704409999860218, "count": 2, "is_parallel": true, "self": 0.0007704409999860218 } } }, "UnityEnvironment.step": { "total": 0.04832471899999291, "count": 1, "is_parallel": true, "self": 0.0003528320000327767, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002413969999679466, "count": 1, "is_parallel": true, "self": 0.0002413969999679466 }, "communicator.exchange": { "total": 0.046990107999988595, "count": 1, "is_parallel": true, "self": 0.046990107999988595 }, "steps_from_proto": { "total": 0.0007403820000035921, "count": 1, "is_parallel": true, "self": 0.00019682699996792508, "children": { "_process_rank_one_or_two_observation": { "total": 0.000543555000035667, "count": 2, "is_parallel": true, "self": 0.000543555000035667 } } } } } } }, "UnityEnvironment.step": { "total": 1250.770506394998, "count": 231457, "is_parallel": true, "self": 38.68743735794442, "children": { "UnityEnvironment._generate_step_input": { "total": 78.14293716208084, "count": 231457, "is_parallel": true, "self": 78.14293716208084 }, "communicator.exchange": { "total": 1041.1124437379867, "count": 231457, "is_parallel": true, "self": 1041.1124437379867 }, "steps_from_proto": { "total": 92.82768813698601, "count": 231457, "is_parallel": true, "self": 32.83356885497318, "children": { "_process_rank_one_or_two_observation": { "total": 59.99411928201283, "count": 462914, "is_parallel": true, "self": 59.99411928201283 } } } } } } } } } } }, "trainer_advance": { "total": 500.9925824778288, "count": 231458, "self": 6.357669653803953, "children": { "process_trajectory": { "total": 125.01174927002495, "count": 231458, "self": 123.57592335202418, "children": { "RLTrainer._checkpoint": { "total": 1.4358259180007735, "count": 10, "self": 1.4358259180007735 } } }, "_update_policy": { "total": 369.6231635539999, "count": 96, "self": 310.883741777999, "children": { "TorchPPOOptimizer.update": { "total": 58.73942177600094, "count": 2880, "self": 58.73942177600094 } } } } } } }, "trainer_threads": { "total": 1.359000179945724e-06, "count": 1, "self": 1.359000179945724e-06 }, "TrainerController._save_models": { "total": 0.1948341080001228, "count": 1, "self": 0.002648459999818442, "children": { "RLTrainer._checkpoint": { "total": 0.19218564800030435, "count": 1, "self": 0.19218564800030435 } } } } } } }