ppo-Huggy / run_logs /timers.json
GerardCB's picture
Huggy
0c038b3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4062718152999878,
"min": 1.4062718152999878,
"max": 1.4264708757400513,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70468.28125,
"min": 68524.546875,
"max": 78103.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.43432574430823,
"min": 81.69370860927152,
"max": 401.368,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49354.0,
"min": 48884.0,
"max": 50171.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999957.0,
"min": 49940.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999957.0,
"min": 49940.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4216463565826416,
"min": 0.022763438522815704,
"max": 2.495269775390625,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1382.760009765625,
"min": 2.8226664066314697,
"max": 1473.81591796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.707579405107348,
"min": 1.714786262041138,
"max": 4.0323460766402155,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2117.0278403162956,
"min": 212.63349649310112,
"max": 2308.9366633296013,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.707579405107348,
"min": 1.714786262041138,
"max": 4.0323460766402155,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2117.0278403162956,
"min": 212.63349649310112,
"max": 2308.9366633296013,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01696816049192825,
"min": 0.012782249416341075,
"max": 0.018924682063273697,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05090448147578475,
"min": 0.02747249096670809,
"max": 0.05410179065608342,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053522673042284113,
"min": 0.022448892363657554,
"max": 0.06467568340400855,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16056801912685234,
"min": 0.04489778472731511,
"max": 0.17443629292150337,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5537988154333266e-06,
"min": 3.5537988154333266e-06,
"max": 0.00029536830154389994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.066139644629998e-05,
"min": 1.066139644629998e-05,
"max": 0.0008441574186142001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118456666666668,
"min": 0.10118456666666668,
"max": 0.1984561,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30355370000000004,
"min": 0.20750085000000004,
"max": 0.5813858,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.910987666666657e-05,
"min": 6.910987666666657e-05,
"max": 0.00492295939,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002073296299999997,
"min": 0.0002073296299999997,
"max": 0.014071151420000002,
"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": "1721314660",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1721317001"
},
"total": 2340.8571435179997,
"count": 1,
"self": 0.4361060070000349,
"children": {
"run_training.setup": {
"total": 0.060804715000017495,
"count": 1,
"self": 0.060804715000017495
},
"TrainerController.start_learning": {
"total": 2340.3602327959998,
"count": 1,
"self": 4.106485230950511,
"children": {
"TrainerController._reset_env": {
"total": 3.3580092069999523,
"count": 1,
"self": 3.3580092069999523
},
"TrainerController.advance": {
"total": 2332.782362781049,
"count": 232115,
"self": 4.548325169027521,
"children": {
"env_step": {
"total": 1846.7282880550329,
"count": 232115,
"self": 1516.3825168670394,
"children": {
"SubprocessEnvManager._take_step": {
"total": 327.598536433989,
"count": 232115,
"self": 16.505009830017627,
"children": {
"TorchPolicy.evaluate": {
"total": 311.0935266039714,
"count": 222990,
"self": 311.0935266039714
}
}
},
"workers": {
"total": 2.7472347540044666,
"count": 232115,
"self": 0.0,
"children": {
"worker_root": {
"total": 2333.3298047349294,
"count": 232115,
"is_parallel": true,
"self": 1115.1322883939727,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008522429999970882,
"count": 1,
"is_parallel": true,
"self": 0.00023304299998017086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006192000000169173,
"count": 2,
"is_parallel": true,
"self": 0.0006192000000169173
}
}
},
"UnityEnvironment.step": {
"total": 0.029484464999995907,
"count": 1,
"is_parallel": true,
"self": 0.0003876129999866862,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002273989999821424,
"count": 1,
"is_parallel": true,
"self": 0.0002273989999821424
},
"communicator.exchange": {
"total": 0.028102889000024334,
"count": 1,
"is_parallel": true,
"self": 0.028102889000024334
},
"steps_from_proto": {
"total": 0.0007665640000027452,
"count": 1,
"is_parallel": true,
"self": 0.00020225100007564834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005643129999270968,
"count": 2,
"is_parallel": true,
"self": 0.0005643129999270968
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1218.1975163409568,
"count": 232114,
"is_parallel": true,
"self": 37.91628731612536,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.23121503591,
"count": 232114,
"is_parallel": true,
"self": 79.23121503591
},
"communicator.exchange": {
"total": 1014.4403084690059,
"count": 232114,
"is_parallel": true,
"self": 1014.4403084690059
},
"steps_from_proto": {
"total": 86.60970551991545,
"count": 232114,
"is_parallel": true,
"self": 30.799681628017993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.81002389189746,
"count": 464228,
"is_parallel": true,
"self": 55.81002389189746
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.5057495569886,
"count": 232115,
"self": 6.244709562974151,
"children": {
"process_trajectory": {
"total": 150.01147334901458,
"count": 232115,
"self": 148.55295603301494,
"children": {
"RLTrainer._checkpoint": {
"total": 1.458517315999643,
"count": 10,
"self": 1.458517315999643
}
}
},
"_update_policy": {
"total": 325.24956664499985,
"count": 97,
"self": 261.6582982570036,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.59126838799625,
"count": 2910,
"self": 63.59126838799625
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0809999366756529e-06,
"count": 1,
"self": 1.0809999366756529e-06
},
"TrainerController._save_models": {
"total": 0.1133744960002332,
"count": 1,
"self": 0.0018491390001145191,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11152535700011867,
"count": 1,
"self": 0.11152535700011867
}
}
}
}
}
}
}