ppo-Huggy / run_logs /timers.json
maavaneck's picture
Huggy
364fd3c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4022775888442993,
"min": 1.4022775888442993,
"max": 1.4263097047805786,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69937.1953125,
"min": 69117.1484375,
"max": 78833.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.8605851979346,
"min": 82.78595317725753,
"max": 410.7950819672131,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48723.0,
"min": 48723.0,
"max": 50149.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49930.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49930.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4095265865325928,
"min": 0.07725109905004501,
"max": 2.4817326068878174,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1402.344482421875,
"min": 9.347382545471191,
"max": 1427.34716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6763682326500358,
"min": 1.8966294253660627,
"max": 3.95103646117322,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2139.646311402321,
"min": 229.4921604692936,
"max": 2257.8034579753876,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6763682326500358,
"min": 1.8966294253660627,
"max": 3.95103646117322,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2139.646311402321,
"min": 229.4921604692936,
"max": 2257.8034579753876,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017847553150366163,
"min": 0.012672387099519254,
"max": 0.020210976273907968,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05354265945109849,
"min": 0.02534477419903851,
"max": 0.05828074412032341,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058780172922545004,
"min": 0.023211444479723772,
"max": 0.06094927671882842,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.176340518767635,
"min": 0.046422888959447545,
"max": 0.18284783015648526,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.335248888283331e-06,
"min": 3.335248888283331e-06,
"max": 0.00029533200155599994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0005746664849993e-05,
"min": 1.0005746664849993e-05,
"max": 0.0008441808186063999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111171666666668,
"min": 0.10111171666666668,
"max": 0.19844399999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30333515000000005,
"min": 0.20738655000000006,
"max": 0.5813935999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.547466166666661e-05,
"min": 6.547466166666661e-05,
"max": 0.0049223556,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019642398499999984,
"min": 0.00019642398499999984,
"max": 0.014071540640000001,
"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": "1723980255",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723982706"
},
"total": 2450.893159029,
"count": 1,
"self": 0.4418335779996596,
"children": {
"run_training.setup": {
"total": 0.05710258800002066,
"count": 1,
"self": 0.05710258800002066
},
"TrainerController.start_learning": {
"total": 2450.3942228630003,
"count": 1,
"self": 4.416646011054581,
"children": {
"TrainerController._reset_env": {
"total": 2.565929251000057,
"count": 1,
"self": 2.565929251000057
},
"TrainerController.advance": {
"total": 2443.289048115946,
"count": 232654,
"self": 4.8255064820045845,
"children": {
"env_step": {
"total": 1932.6568528669434,
"count": 232654,
"self": 1590.4899434260374,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.2578903389732,
"count": 232654,
"self": 17.32855589694782,
"children": {
"TorchPolicy.evaluate": {
"total": 321.9293344420254,
"count": 223050,
"self": 321.9293344420254
}
}
},
"workers": {
"total": 2.909019101932927,
"count": 232654,
"self": 0.0,
"children": {
"worker_root": {
"total": 2443.008177841034,
"count": 232654,
"is_parallel": true,
"self": 1160.404556070037,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008920279999529157,
"count": 1,
"is_parallel": true,
"self": 0.0002367820000017673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006552459999511484,
"count": 2,
"is_parallel": true,
"self": 0.0006552459999511484
}
}
},
"UnityEnvironment.step": {
"total": 0.030369116999963808,
"count": 1,
"is_parallel": true,
"self": 0.0003910579999910624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002733100000114064,
"count": 1,
"is_parallel": true,
"self": 0.0002733100000114064
},
"communicator.exchange": {
"total": 0.02896670899997389,
"count": 1,
"is_parallel": true,
"self": 0.02896670899997389
},
"steps_from_proto": {
"total": 0.0007380399999874498,
"count": 1,
"is_parallel": true,
"self": 0.00019162700004926592,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005464129999381839,
"count": 2,
"is_parallel": true,
"self": 0.0005464129999381839
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1282.603621770997,
"count": 232653,
"is_parallel": true,
"self": 38.62402932207942,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.32278377593684,
"count": 232653,
"is_parallel": true,
"self": 83.32278377593684
},
"communicator.exchange": {
"total": 1069.3918029449856,
"count": 232653,
"is_parallel": true,
"self": 1069.3918029449856
},
"steps_from_proto": {
"total": 91.26500572799534,
"count": 232653,
"is_parallel": true,
"self": 34.2446975041762,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.02030822381914,
"count": 465306,
"is_parallel": true,
"self": 57.02030822381914
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 505.80668876699826,
"count": 232654,
"self": 6.965700886007539,
"children": {
"process_trajectory": {
"total": 161.82696974699093,
"count": 232654,
"self": 160.50500526899123,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3219644779996997,
"count": 10,
"self": 1.3219644779996997
}
}
},
"_update_policy": {
"total": 337.0140181339998,
"count": 97,
"self": 272.7822922050033,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.23172592899652,
"count": 2910,
"self": 64.23172592899652
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2239997886354104e-06,
"count": 1,
"self": 1.2239997886354104e-06
},
"TrainerController._save_models": {
"total": 0.12259826099989368,
"count": 1,
"self": 0.0018706159999055672,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12072764499998812,
"count": 1,
"self": 0.12072764499998812
}
}
}
}
}
}
}