ppo-Huggy / run_logs /timers.json
CaphAlderamin's picture
Huggy
5df0db7 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4035099744796753,
"min": 1.4035090208053589,
"max": 1.4282716512680054,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67489.1796875,
"min": 67320.25,
"max": 77156.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.62025316455696,
"min": 91.05893186003684,
"max": 378.43939393939394,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49590.0,
"min": 48824.0,
"max": 50236.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999392.0,
"min": 49979.0,
"max": 1999392.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999392.0,
"min": 49979.0,
"max": 1999392.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2977077960968018,
"min": 0.13238227367401123,
"max": 2.3941810131073,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1089.113525390625,
"min": 18.136371612548828,
"max": 1253.304443359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5327187093752848,
"min": 1.8251356673936774,
"max": 3.8277680379252472,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1674.508668243885,
"min": 250.0435864329338,
"max": 2025.7110387086868,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5327187093752848,
"min": 1.8251356673936774,
"max": 3.8277680379252472,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1674.508668243885,
"min": 250.0435864329338,
"max": 2025.7110387086868,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01976699896622449,
"min": 0.012910465530209574,
"max": 0.021862093322367097,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03953399793244898,
"min": 0.025820931060419147,
"max": 0.056520750631655875,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04437021228174369,
"min": 0.022178511352588734,
"max": 0.05968256431321303,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08874042456348738,
"min": 0.04435702270517747,
"max": 0.1652813437084357,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.15487361507501e-06,
"min": 4.15487361507501e-06,
"max": 0.0002952428265857249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.30974723015002e-06,
"min": 8.30974723015002e-06,
"max": 0.0008437630687456498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10138492500000001,
"min": 0.10138492500000001,
"max": 0.19841427500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20276985000000003,
"min": 0.20276985000000003,
"max": 0.5812543500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.91077575000002e-05,
"min": 7.91077575000002e-05,
"max": 0.0049208723225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001582155150000004,
"min": 0.0001582155150000004,
"max": 0.014064592065,
"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": "1708349969",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708352484"
},
"total": 2514.559950319,
"count": 1,
"self": 0.7002374399999098,
"children": {
"run_training.setup": {
"total": 0.057440630000030524,
"count": 1,
"self": 0.057440630000030524
},
"TrainerController.start_learning": {
"total": 2513.802272249,
"count": 1,
"self": 4.6166686529782055,
"children": {
"TrainerController._reset_env": {
"total": 3.1659495779999816,
"count": 1,
"self": 3.1659495779999816
},
"TrainerController.advance": {
"total": 2505.843187627022,
"count": 231126,
"self": 5.19151120026936,
"children": {
"env_step": {
"total": 2028.8038673168762,
"count": 231126,
"self": 1675.6128749616603,
"children": {
"SubprocessEnvManager._take_step": {
"total": 350.14232615613054,
"count": 231126,
"self": 18.70913227522118,
"children": {
"TorchPolicy.evaluate": {
"total": 331.43319388090936,
"count": 222901,
"self": 331.43319388090936
}
}
},
"workers": {
"total": 3.0486661990853463,
"count": 231126,
"self": 0.0,
"children": {
"worker_root": {
"total": 2505.921838330075,
"count": 231126,
"is_parallel": true,
"self": 1143.1403858720187,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010705609999490662,
"count": 1,
"is_parallel": true,
"self": 0.00029988699998284574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007706739999662204,
"count": 2,
"is_parallel": true,
"self": 0.0007706739999662204
}
}
},
"UnityEnvironment.step": {
"total": 0.03111953000001222,
"count": 1,
"is_parallel": true,
"self": 0.0003806810000241967,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021629999997685445,
"count": 1,
"is_parallel": true,
"self": 0.00021629999997685445
},
"communicator.exchange": {
"total": 0.029772322000042095,
"count": 1,
"is_parallel": true,
"self": 0.029772322000042095
},
"steps_from_proto": {
"total": 0.0007502269999690725,
"count": 1,
"is_parallel": true,
"self": 0.00021527099994500531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005349560000240672,
"count": 2,
"is_parallel": true,
"self": 0.0005349560000240672
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1362.7814524580563,
"count": 231125,
"is_parallel": true,
"self": 42.740990723179266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.66996613601225,
"count": 231125,
"is_parallel": true,
"self": 90.66996613601225
},
"communicator.exchange": {
"total": 1131.70189757394,
"count": 231125,
"is_parallel": true,
"self": 1131.70189757394
},
"steps_from_proto": {
"total": 97.66859802492462,
"count": 231125,
"is_parallel": true,
"self": 36.48266547690537,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.18593254801925,
"count": 462250,
"is_parallel": true,
"self": 61.18593254801925
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 471.84780910987627,
"count": 231126,
"self": 7.257109965857865,
"children": {
"process_trajectory": {
"total": 154.74519740101977,
"count": 231126,
"self": 153.41795091402054,
"children": {
"RLTrainer._checkpoint": {
"total": 1.327246486999229,
"count": 10,
"self": 1.327246486999229
}
}
},
"_update_policy": {
"total": 309.84550174299864,
"count": 96,
"self": 246.87771681200695,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.967784930991684,
"count": 2880,
"self": 62.967784930991684
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3879998732591048e-06,
"count": 1,
"self": 1.3879998732591048e-06
},
"TrainerController._save_models": {
"total": 0.1764650029999757,
"count": 1,
"self": 0.0030811669998911384,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17338383600008456,
"count": 1,
"self": 0.17338383600008456
}
}
}
}
}
}
}