ppo-Huggy / run_logs /timers.json
stanidiener's picture
Huggy
df46184
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066622257232666,
"min": 1.4066622257232666,
"max": 1.427818775177002,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70425.953125,
"min": 68235.2890625,
"max": 78378.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.33035714285714,
"min": 79.9126213592233,
"max": 412.8264462809917,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49465.0,
"min": 49179.0,
"max": 50057.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999947.0,
"min": 49730.0,
"max": 1999947.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999947.0,
"min": 49730.0,
"max": 1999947.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5221469402313232,
"min": 0.12066003680229187,
"max": 2.5221469402313232,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1412.4022216796875,
"min": 14.479204177856445,
"max": 1494.4752197265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.879204576675381,
"min": 1.8721905663609504,
"max": 3.9011061338015964,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2172.3545629382133,
"min": 224.66286796331406,
"max": 2372.280670762062,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.879204576675381,
"min": 1.8721905663609504,
"max": 3.9011061338015964,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2172.3545629382133,
"min": 224.66286796331406,
"max": 2372.280670762062,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01538685063335126,
"min": 0.013187940225664836,
"max": 0.02075086094264407,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04616055190005378,
"min": 0.026375880451329672,
"max": 0.05729427173791919,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05478298320538468,
"min": 0.02083754775424798,
"max": 0.06382867706318696,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16434894961615404,
"min": 0.04167509550849596,
"max": 0.1799172575275103,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5050488316833393e-06,
"min": 3.5050488316833393e-06,
"max": 0.00029536102654632493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0515146495050018e-05,
"min": 1.0515146495050018e-05,
"max": 0.0008441098686300498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116831666666669,
"min": 0.10116831666666669,
"max": 0.19845367500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350495000000005,
"min": 0.20749850000000003,
"max": 0.58136995,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.829900166666678e-05,
"min": 6.829900166666678e-05,
"max": 0.004922838382500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020489700500000033,
"min": 0.00020489700500000033,
"max": 0.014070360505,
"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": "1694700926",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694703430"
},
"total": 2504.2049436810003,
"count": 1,
"self": 0.43581357900029616,
"children": {
"run_training.setup": {
"total": 0.04372563600003332,
"count": 1,
"self": 0.04372563600003332
},
"TrainerController.start_learning": {
"total": 2503.725404466,
"count": 1,
"self": 4.485863849077305,
"children": {
"TrainerController._reset_env": {
"total": 4.178164085999981,
"count": 1,
"self": 4.178164085999981
},
"TrainerController.advance": {
"total": 2494.9153964989227,
"count": 232301,
"self": 4.575582361858324,
"children": {
"env_step": {
"total": 1923.258742589085,
"count": 232301,
"self": 1629.9121740629937,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.32662593605676,
"count": 232301,
"self": 16.611459937056566,
"children": {
"TorchPolicy.evaluate": {
"total": 273.7151659990002,
"count": 222981,
"self": 273.7151659990002
}
}
},
"workers": {
"total": 3.019942590034418,
"count": 232301,
"self": 0.0,
"children": {
"worker_root": {
"total": 2496.074205594004,
"count": 232301,
"is_parallel": true,
"self": 1161.8068197350894,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008854599999494894,
"count": 1,
"is_parallel": true,
"self": 0.0002637329999402027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006217270000092867,
"count": 2,
"is_parallel": true,
"self": 0.0006217270000092867
}
}
},
"UnityEnvironment.step": {
"total": 0.029902837999998155,
"count": 1,
"is_parallel": true,
"self": 0.0003664889999299703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021846700002470243,
"count": 1,
"is_parallel": true,
"self": 0.00021846700002470243
},
"communicator.exchange": {
"total": 0.028506590000006327,
"count": 1,
"is_parallel": true,
"self": 0.028506590000006327
},
"steps_from_proto": {
"total": 0.000811292000037156,
"count": 1,
"is_parallel": true,
"self": 0.0002406520000022283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005706400000349277,
"count": 2,
"is_parallel": true,
"self": 0.0005706400000349277
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1334.2673858589146,
"count": 232300,
"is_parallel": true,
"self": 40.79928550290242,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.43550674299871,
"count": 232300,
"is_parallel": true,
"self": 82.43550674299871
},
"communicator.exchange": {
"total": 1110.2262383179577,
"count": 232300,
"is_parallel": true,
"self": 1110.2262383179577
},
"steps_from_proto": {
"total": 100.80635529505565,
"count": 232300,
"is_parallel": true,
"self": 35.65487255306954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.15148274198611,
"count": 464600,
"is_parallel": true,
"self": 65.15148274198611
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 567.0810715479795,
"count": 232301,
"self": 6.62584615112155,
"children": {
"process_trajectory": {
"total": 142.13984919785912,
"count": 232301,
"self": 140.62650541985988,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5133437779992391,
"count": 10,
"self": 1.5133437779992391
}
}
},
"_update_policy": {
"total": 418.31537619899876,
"count": 97,
"self": 357.35603478598443,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.95934141301433,
"count": 2910,
"self": 60.95934141301433
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1249999261053745e-06,
"count": 1,
"self": 1.1249999261053745e-06
},
"TrainerController._save_models": {
"total": 0.1459789069999715,
"count": 1,
"self": 0.0019767029998547514,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14400220400011676,
"count": 1,
"self": 0.14400220400011676
}
}
}
}
}
}
}