ppo-Huggy / run_logs /timers.json
jiang9527li's picture
Huggy
80f8128
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072949886322021,
"min": 1.4072949886322021,
"max": 1.4271352291107178,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71383.6328125,
"min": 69264.7421875,
"max": 77901.2109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.15194346289752,
"min": 87.15194346289752,
"max": 394.5234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49328.0,
"min": 48908.0,
"max": 50499.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49998.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49998.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.346203565597534,
"min": 0.19554495811462402,
"max": 2.4476101398468018,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1327.951171875,
"min": 24.834209442138672,
"max": 1327.951171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6070361160558018,
"min": 1.7882852448722508,
"max": 3.883914573232555,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2041.582441687584,
"min": 227.11222609877586,
"max": 2085.662125825882,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6070361160558018,
"min": 1.7882852448722508,
"max": 3.883914573232555,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2041.582441687584,
"min": 227.11222609877586,
"max": 2085.662125825882,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017421746692141624,
"min": 0.014721823448780924,
"max": 0.021138082456471034,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05226524007642487,
"min": 0.02952746880958633,
"max": 0.0634142473694131,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056126410058803027,
"min": 0.020040641818195582,
"max": 0.058406801956395304,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16837923017640907,
"min": 0.040081283636391164,
"max": 0.16837923017640907,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.230198923300002e-06,
"min": 3.230198923300002e-06,
"max": 0.0002952708015764,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.690596769900007e-06,
"min": 9.690596769900007e-06,
"max": 0.00084383476872175,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010767,
"min": 0.1010767,
"max": 0.1984236000000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032301,
"min": 0.20729354999999994,
"max": 0.5812782500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.372733000000006e-05,
"min": 6.372733000000006e-05,
"max": 0.004921337639999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019118199000000018,
"min": 0.00019118199000000018,
"max": 0.014065784674999996,
"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": "1695712772",
"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": "1695715579"
},
"total": 2807.5871335849997,
"count": 1,
"self": 0.4429847459996381,
"children": {
"run_training.setup": {
"total": 0.05125272700001915,
"count": 1,
"self": 0.05125272700001915
},
"TrainerController.start_learning": {
"total": 2807.0928961120003,
"count": 1,
"self": 5.432044447002681,
"children": {
"TrainerController._reset_env": {
"total": 4.457425065000052,
"count": 1,
"self": 4.457425065000052
},
"TrainerController.advance": {
"total": 2797.0719636749977,
"count": 231763,
"self": 5.74324961186494,
"children": {
"env_step": {
"total": 2167.721618082933,
"count": 231763,
"self": 1831.0562218958264,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.03679494400285,
"count": 231763,
"self": 19.801384213988058,
"children": {
"TorchPolicy.evaluate": {
"total": 313.2354107300148,
"count": 222970,
"self": 313.2354107300148
}
}
},
"workers": {
"total": 3.628601243103958,
"count": 231763,
"self": 0.0,
"children": {
"worker_root": {
"total": 2798.1156238190683,
"count": 231763,
"is_parallel": true,
"self": 1302.9956716930303,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009450970001125825,
"count": 1,
"is_parallel": true,
"self": 0.00024071400025604817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007043829998565343,
"count": 2,
"is_parallel": true,
"self": 0.0007043829998565343
}
}
},
"UnityEnvironment.step": {
"total": 0.03345315899991874,
"count": 1,
"is_parallel": true,
"self": 0.00038468699995064526,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002366640001127962,
"count": 1,
"is_parallel": true,
"self": 0.0002366640001127962
},
"communicator.exchange": {
"total": 0.03204143599987219,
"count": 1,
"is_parallel": true,
"self": 0.03204143599987219
},
"steps_from_proto": {
"total": 0.0007903719999831083,
"count": 1,
"is_parallel": true,
"self": 0.00021945699995740142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005709150000257068,
"count": 2,
"is_parallel": true,
"self": 0.0005709150000257068
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1495.119952126038,
"count": 231762,
"is_parallel": true,
"self": 45.6834089293136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.32326318589617,
"count": 231762,
"is_parallel": true,
"self": 88.32326318589617
},
"communicator.exchange": {
"total": 1248.2358110998764,
"count": 231762,
"is_parallel": true,
"self": 1248.2358110998764
},
"steps_from_proto": {
"total": 112.87746891095185,
"count": 231762,
"is_parallel": true,
"self": 38.64702070878252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.23044820216933,
"count": 463524,
"is_parallel": true,
"self": 74.23044820216933
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 623.6070959801998,
"count": 231763,
"self": 8.322077859243564,
"children": {
"process_trajectory": {
"total": 151.06455989295796,
"count": 231763,
"self": 149.4339148429574,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6306450500005667,
"count": 10,
"self": 1.6306450500005667
}
}
},
"_update_policy": {
"total": 464.2204582279983,
"count": 97,
"self": 397.59291372700227,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.62754450099601,
"count": 2910,
"self": 66.62754450099601
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0289995771017857e-06,
"count": 1,
"self": 1.0289995771017857e-06
},
"TrainerController._save_models": {
"total": 0.13146189600047364,
"count": 1,
"self": 0.0020608810000339872,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12940101500043966,
"count": 1,
"self": 0.12940101500043966
}
}
}
}
}
}
}