{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4079703092575073, "min": 1.4079703092575073, "max": 1.427160382270813, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70392.8828125, "min": 68583.84375, "max": 76626.484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.80610412926391, "min": 84.58952702702703, "max": 393.33858267716533, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49465.0, "min": 48859.0, "max": 50168.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999943.0, "min": 49699.0, "max": 1999943.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999943.0, "min": 49699.0, "max": 1999943.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4578139781951904, "min": 0.06583267450332642, "max": 2.4744949340820312, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1369.00244140625, "min": 8.294917106628418, "max": 1426.7652587890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.760987071096362, "min": 1.6535379250371267, "max": 3.893679956595103, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2094.8697986006737, "min": 208.34577855467796, "max": 2241.5250130295753, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.760987071096362, "min": 1.6535379250371267, "max": 3.893679956595103, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2094.8697986006737, "min": 208.34577855467796, "max": 2241.5250130295753, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015665434816845743, "min": 0.013653189906350841, "max": 0.020863722384415775, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04699630445053723, "min": 0.027306379812701682, "max": 0.06259116715324732, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05611459145115482, "min": 0.022541155604024726, "max": 0.059774056242571934, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16834377435346445, "min": 0.04508231120804945, "max": 0.1793221687277158, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.501148832983338e-06, "min": 3.501148832983338e-06, "max": 0.0002952705015765, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0503446498950014e-05, "min": 1.0503446498950014e-05, "max": 0.0008439327186891001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116701666666666, "min": 0.10116701666666666, "max": 0.19842350000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30350105, "min": 0.20746430000000005, "max": 0.5813109000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.823413166666677e-05, "min": 6.823413166666677e-05, "max": 0.0049213326500000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002047023950000003, "min": 0.0002047023950000003, "max": 0.01406741391, "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": "1712739096", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712741701" }, "total": 2605.356360869, "count": 1, "self": 0.43830610699978934, "children": { "run_training.setup": { "total": 0.055731752000042434, "count": 1, "self": 0.055731752000042434 }, "TrainerController.start_learning": { "total": 2604.86232301, "count": 1, "self": 4.791387242934434, "children": { "TrainerController._reset_env": { "total": 3.31993685000009, "count": 1, "self": 3.31993685000009 }, "TrainerController.advance": { "total": 2596.6255624210658, "count": 232402, "self": 5.256633932020577, "children": { "env_step": { "total": 2098.497823083885, "count": 232402, "self": 1738.7118884809506, "children": { "SubprocessEnvManager._take_step": { "total": 356.5369373129712, "count": 232402, "self": 18.884821314004284, "children": { "TorchPolicy.evaluate": { "total": 337.6521159989669, "count": 222984, "self": 337.6521159989669 } } }, "workers": { "total": 3.2489972899631994, "count": 232402, "self": 0.0, "children": { "worker_root": { "total": 2596.8997921751484, "count": 232402, "is_parallel": true, "self": 1197.3668570421626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009845749999612963, "count": 1, "is_parallel": true, "self": 0.00027215499994781567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007124200000134806, "count": 2, "is_parallel": true, "self": 0.0007124200000134806 } } }, "UnityEnvironment.step": { "total": 0.04995689999998376, "count": 1, "is_parallel": true, "self": 0.0004772830000092654, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020915699997203774, "count": 1, "is_parallel": true, "self": 0.00020915699997203774 }, "communicator.exchange": { "total": 0.04687044699994658, "count": 1, "is_parallel": true, "self": 0.04687044699994658 }, "steps_from_proto": { "total": 0.0024000130000558784, "count": 1, "is_parallel": true, "self": 0.0002612490001183687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021387639999375097, "count": 2, "is_parallel": true, "self": 0.0021387639999375097 } } } } } } }, "UnityEnvironment.step": { "total": 1399.5329351329858, "count": 232401, "is_parallel": true, "self": 41.4054194969483, "children": { "UnityEnvironment._generate_step_input": { "total": 91.42095840796765, "count": 232401, "is_parallel": true, "self": 91.42095840796765 }, "communicator.exchange": { "total": 1167.2075444509783, "count": 232401, "is_parallel": true, "self": 1167.2075444509783 }, "steps_from_proto": { "total": 99.4990127770916, "count": 232401, "is_parallel": true, "self": 37.851627003158114, "children": { "_process_rank_one_or_two_observation": { "total": 61.64738577393348, "count": 464802, "is_parallel": true, "self": 61.64738577393348 } } } } } } } } } } }, "trainer_advance": { "total": 492.87110540516016, "count": 232402, "self": 6.989338416059127, "children": { "process_trajectory": { "total": 168.7658904951012, "count": 232402, "self": 167.29467267610187, "children": { "RLTrainer._checkpoint": { "total": 1.471217818999321, "count": 10, "self": 1.471217818999321 } } }, "_update_policy": { "total": 317.11587649399985, "count": 97, "self": 254.2189468649808, "children": { "TorchPPOOptimizer.update": { "total": 62.89692962901904, "count": 2910, "self": 62.89692962901904 } } } } } } }, "trainer_threads": { "total": 1.0909998309216462e-06, "count": 1, "self": 1.0909998309216462e-06 }, "TrainerController._save_models": { "total": 0.12543540500018935, "count": 1, "self": 0.0020573420001710474, "children": { "RLTrainer._checkpoint": { "total": 0.1233780630000183, "count": 1, "self": 0.1233780630000183 } } } } } } }