{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4206538200378418, "min": 1.4195961952209473, "max": 1.4277534484863281, "count": 20 }, "Huggy.Policy.Entropy.sum": { "value": 71728.8125, "min": 68157.8203125, "max": 77207.578125, "count": 20 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.13269230769231, "min": 89.22909090909091, "max": 390.4609375, "count": 20 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49469.0, "min": 48864.0, "max": 50221.0, "count": 20 }, "Huggy.Step.mean": { "value": 999998.0, "min": 49575.0, "max": 999998.0, "count": 20 }, "Huggy.Step.sum": { "value": 999998.0, "min": 49575.0, "max": 999998.0, "count": 20 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3513858318328857, "min": 0.07961344718933105, "max": 2.364870071411133, "count": 20 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1222.7205810546875, "min": 10.110907554626465, "max": 1284.0537109375, "count": 20 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.736752470296163, "min": 1.6877522482646732, "max": 3.8617649473823032, "count": 20 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1943.1112845540047, "min": 214.3445355296135, "max": 1988.774264574051, "count": 20 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.736752470296163, "min": 1.6877522482646732, "max": 3.8617649473823032, "count": 20 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1943.1112845540047, "min": 214.3445355296135, "max": 1988.774264574051, "count": 20 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01936078530488885, "min": 0.01407309361723795, "max": 0.01936078530488885, "count": 20 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0387215706097777, "min": 0.0281461872344759, "max": 0.05524295394764825, "count": 20 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0679251428693533, "min": 0.02195577519014478, "max": 0.0693905954559644, "count": 20 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1358502857387066, "min": 0.04391155038028956, "max": 0.2081717863678932, "count": 20 }, "Huggy.Policy.LearningRate.mean": { "value": 6.057997980700005e-06, "min": 6.057997980700005e-06, "max": 0.0002907261030913, "count": 20 }, "Huggy.Policy.LearningRate.sum": { "value": 1.211599596140001e-05, "min": 1.211599596140001e-05, "max": 0.0007874697375100999, "count": 20 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10201930000000001, "min": 0.10201930000000001, "max": 0.1969087, "count": 20 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20403860000000001, "min": 0.20403860000000001, "max": 0.5624899, "count": 20 }, "Huggy.Policy.Beta.mean": { "value": 0.00011076307000000007, "min": 0.00011076307000000007, "max": 0.004845744129999999, "count": 20 }, "Huggy.Policy.Beta.sum": { "value": 0.00022152614000000014, "min": 0.00022152614000000014, "max": 0.013128246009999997, "count": 20 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713769860", "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": "1713772146" }, "total": 2286.614153992, "count": 1, "self": 0.6461835469999642, "children": { "run_training.setup": { "total": 0.07811035299982905, "count": 1, "self": 0.07811035299982905 }, "TrainerController.start_learning": { "total": 2285.889860092, "count": 1, "self": 4.493359254074221, "children": { "TrainerController._reset_env": { "total": 4.11450236099995, "count": 1, "self": 4.11450236099995 }, "TrainerController.advance": { "total": 2277.133671704926, "count": 115211, "self": 4.355452661052823, "children": { "env_step": { "total": 1534.937234708915, "count": 115211, "self": 1283.7309480330282, "children": { "SubprocessEnvManager._take_step": { "total": 248.33795249493278, "count": 115211, "self": 16.104940271989108, "children": { "TorchPolicy.evaluate": { "total": 232.23301222294367, "count": 111552, "self": 232.23301222294367 } } }, "workers": { "total": 2.8683341809539797, "count": 115211, "self": 0.0, "children": { "worker_root": { "total": 2278.751882867932, "count": 115211, "is_parallel": true, "self": 1262.442605809985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019926059999306744, "count": 1, "is_parallel": true, "self": 0.00048418299979857693, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015084230001320975, "count": 2, "is_parallel": true, "self": 0.0015084230001320975 } } }, "UnityEnvironment.step": { "total": 0.038364251000075456, "count": 1, "is_parallel": true, "self": 0.0005305580000367627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002882840001348086, "count": 1, "is_parallel": true, "self": 0.0002882840001348086 }, "communicator.exchange": { "total": 0.036546264999969935, "count": 1, "is_parallel": true, "self": 0.036546264999969935 }, "steps_from_proto": { "total": 0.000999143999933949, "count": 1, "is_parallel": true, "self": 0.00025248199995075993, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007466619999831892, "count": 2, "is_parallel": true, "self": 0.0007466619999831892 } } } } } } }, "UnityEnvironment.step": { "total": 1016.3092770579472, "count": 115210, "is_parallel": true, "self": 32.88374314081875, "children": { "UnityEnvironment._generate_step_input": { "total": 56.41999238398353, "count": 115210, "is_parallel": true, "self": 56.41999238398353 }, "communicator.exchange": { "total": 854.527186522155, "count": 115210, "is_parallel": true, "self": 854.527186522155 }, "steps_from_proto": { "total": 72.47835501098984, "count": 115210, "is_parallel": true, "self": 22.983809176835166, "children": { "_process_rank_one_or_two_observation": { "total": 49.49454583415468, "count": 230420, "is_parallel": true, "self": 49.49454583415468 } } } } } } } } } } }, "trainer_advance": { "total": 737.8409843349584, "count": 115211, "self": 6.6841305909092625, "children": { "process_trajectory": { "total": 118.7770517320489, "count": 115211, "self": 118.04152962204967, "children": { "RLTrainer._checkpoint": { "total": 0.7355221099992377, "count": 5, "self": 0.7355221099992377 } } }, "_update_policy": { "total": 612.3798020120003, "count": 48, "self": 154.99107031098947, "children": { "TorchPPOOptimizer.update": { "total": 457.3887317010108, "count": 1440, "self": 457.3887317010108 } } } } } } }, "trainer_threads": { "total": 1.0339999789721332e-06, "count": 1, "self": 1.0339999789721332e-06 }, "TrainerController._save_models": { "total": 0.14832573800003956, "count": 1, "self": 0.006053433000033692, "children": { "RLTrainer._checkpoint": { "total": 0.14227230500000587, "count": 1, "self": 0.14227230500000587 } } } } } } }