{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3984004259109497, "min": 1.3984004259109497, "max": 1.4258220195770264, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70072.4453125, "min": 68316.203125, "max": 79636.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.26821192052981, "min": 75.1829268292683, "max": 393.9375, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49690.0, "min": 48870.0, "max": 50424.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999595.0, "min": 49802.0, "max": 1999595.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999595.0, "min": 49802.0, "max": 1999595.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.52866268157959, "min": -0.06104308366775513, "max": 2.528871774673462, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1527.312255859375, "min": -7.752471446990967, "max": 1628.839599609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9760195414554205, "min": 1.8409916941575177, "max": 4.0708684853953345, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2401.515803039074, "min": 233.80594515800476, "max": 2505.2376331090927, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9760195414554205, "min": 1.8409916941575177, "max": 4.0708684853953345, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2401.515803039074, "min": 233.80594515800476, "max": 2505.2376331090927, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017563357684881944, "min": 0.012440926182352995, "max": 0.02127244893927127, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05269007305464583, "min": 0.02488185236470599, "max": 0.05599091310014046, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06344223125941223, "min": 0.023205468182762465, "max": 0.06799485286076863, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1903266937782367, "min": 0.04833790219078461, "max": 0.2039845585823059, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6290987903333373e-06, "min": 3.6290987903333373e-06, "max": 0.00029537100154299994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0887296371000011e-05, "min": 1.0887296371000011e-05, "max": 0.0008439075186975, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120966666666666, "min": 0.10120966666666666, "max": 0.198457, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.303629, "min": 0.2075747, "max": 0.5813024999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.036236666666674e-05, "min": 7.036236666666674e-05, "max": 0.004923004299999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021108710000000024, "min": 0.00021108710000000024, "max": 0.014066994750000002, "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": "1699650053", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699652784" }, "total": 2731.768703732, "count": 1, "self": 0.4903652900002271, "children": { "run_training.setup": { "total": 0.04684434099999635, "count": 1, "self": 0.04684434099999635 }, "TrainerController.start_learning": { "total": 2731.231494101, "count": 1, "self": 5.186008575064079, "children": { "TrainerController._reset_env": { "total": 8.587311021000005, "count": 1, "self": 8.587311021000005 }, "TrainerController.advance": { "total": 2717.353018729936, "count": 232981, "self": 5.368758293058818, "children": { "env_step": { "total": 2155.3443385689866, "count": 232981, "self": 1777.5093603190962, "children": { "SubprocessEnvManager._take_step": { "total": 374.44740342094735, "count": 232981, "self": 19.878807612925016, "children": { "TorchPolicy.evaluate": { "total": 354.56859580802234, "count": 222938, "self": 354.56859580802234 } } }, "workers": { "total": 3.3875748289428884, "count": 232981, "self": 0.0, "children": { "worker_root": { "total": 2722.70476781595, "count": 232981, "is_parallel": true, "self": 1283.8007703299245, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008854960000235224, "count": 1, "is_parallel": true, "self": 0.0002383649999728732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006471310000506492, "count": 2, "is_parallel": true, "self": 0.0006471310000506492 } } }, "UnityEnvironment.step": { "total": 0.053919345999929646, "count": 1, "is_parallel": true, "self": 0.0003184379997946962, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017981300004521472, "count": 1, "is_parallel": true, "self": 0.00017981300004521472 }, "communicator.exchange": { "total": 0.05268517400008932, "count": 1, "is_parallel": true, "self": 0.05268517400008932 }, "steps_from_proto": { "total": 0.0007359210000004168, "count": 1, "is_parallel": true, "self": 0.00017327800003386074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005626429999665561, "count": 2, "is_parallel": true, "self": 0.0005626429999665561 } } } } } } }, "UnityEnvironment.step": { "total": 1438.9039974860257, "count": 232980, "is_parallel": true, "self": 44.12173702007385, "children": { "UnityEnvironment._generate_step_input": { "total": 88.75370166495975, "count": 232980, "is_parallel": true, "self": 88.75370166495975 }, "communicator.exchange": { "total": 1206.2927672360288, "count": 232980, "is_parallel": true, "self": 1206.2927672360288 }, "steps_from_proto": { "total": 99.73579156496328, "count": 232980, "is_parallel": true, "self": 34.000954624924816, "children": { "_process_rank_one_or_two_observation": { "total": 65.73483694003846, "count": 465960, "is_parallel": true, "self": 65.73483694003846 } } } } } } } } } } }, "trainer_advance": { "total": 556.6399218678906, "count": 232981, "self": 7.711653443960472, "children": { "process_trajectory": { "total": 172.1275976729297, "count": 232981, "self": 170.71869812092962, "children": { "RLTrainer._checkpoint": { "total": 1.4088995520000935, "count": 10, "self": 1.4088995520000935 } } }, "_update_policy": { "total": 376.80067075100044, "count": 97, "self": 308.65315573501516, "children": { "TorchPPOOptimizer.update": { "total": 68.14751501598528, "count": 2910, "self": 68.14751501598528 } } } } } } }, "trainer_threads": { "total": 9.6099984148168e-07, "count": 1, "self": 9.6099984148168e-07 }, "TrainerController._save_models": { "total": 0.10515481399988857, "count": 1, "self": 0.0018858449998333526, "children": { "RLTrainer._checkpoint": { "total": 0.10326896900005522, "count": 1, "self": 0.10326896900005522 } } } } } } }