Loriiis's picture
First Push
ffc672b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7378113865852356,
"min": 0.7378113865852356,
"max": 2.8697216510772705,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7060.85498046875,
"min": 7060.85498046875,
"max": 29420.38671875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.100936889648438,
"min": 0.5250970125198364,
"max": 13.100936889648438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.6826171875,
"min": 101.86882019042969,
"max": 2650.47314453125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07145029757834981,
"min": 0.06213690107707924,
"max": 0.0750477872752348,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28580119031339923,
"min": 0.24854760430831696,
"max": 0.375238936376174,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17969878551130203,
"min": 0.15337767908303981,
"max": 0.2895274818527932,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7187951420452081,
"min": 0.6135107163321593,
"max": 1.4476374092639661,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.704545454545453,
"min": 4.159090909090909,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 183.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 4.159090909090909,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 183.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1698180172",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698180647"
},
"total": 475.00936184299985,
"count": 1,
"self": 0.7799069889999828,
"children": {
"run_training.setup": {
"total": 0.04329581000001781,
"count": 1,
"self": 0.04329581000001781
},
"TrainerController.start_learning": {
"total": 474.18615904399985,
"count": 1,
"self": 0.5883006989927253,
"children": {
"TrainerController._reset_env": {
"total": 8.946511677999979,
"count": 1,
"self": 8.946511677999979
},
"TrainerController.advance": {
"total": 464.5219968500073,
"count": 18207,
"self": 0.2671358960383259,
"children": {
"env_step": {
"total": 464.254860953969,
"count": 18207,
"self": 318.1596577189821,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.81023950997496,
"count": 18207,
"self": 1.461283841019167,
"children": {
"TorchPolicy.evaluate": {
"total": 144.3489556689558,
"count": 18207,
"self": 144.3489556689558
}
}
},
"workers": {
"total": 0.28496372501194855,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.81639497002834,
"count": 18207,
"is_parallel": true,
"self": 232.03260004998197,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006024734999982684,
"count": 1,
"is_parallel": true,
"self": 0.004619701999672543,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014050330003101408,
"count": 10,
"is_parallel": true,
"self": 0.0014050330003101408
}
}
},
"UnityEnvironment.step": {
"total": 0.046961830999862286,
"count": 1,
"is_parallel": true,
"self": 0.0006522409998979128,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031570499982080946,
"count": 1,
"is_parallel": true,
"self": 0.00031570499982080946
},
"communicator.exchange": {
"total": 0.044116666000036275,
"count": 1,
"is_parallel": true,
"self": 0.044116666000036275
},
"steps_from_proto": {
"total": 0.0018772190001072886,
"count": 1,
"is_parallel": true,
"self": 0.00037076499984323164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001506454000264057,
"count": 10,
"is_parallel": true,
"self": 0.001506454000264057
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.78379492004638,
"count": 18206,
"is_parallel": true,
"self": 10.644896266023125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.395932115017786,
"count": 18206,
"is_parallel": true,
"self": 5.395932115017786
},
"communicator.exchange": {
"total": 190.56203881902024,
"count": 18206,
"is_parallel": true,
"self": 190.56203881902024
},
"steps_from_proto": {
"total": 34.18092771998522,
"count": 18206,
"is_parallel": true,
"self": 6.436465247070146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.744462472915075,
"count": 182060,
"is_parallel": true,
"self": 27.744462472915075
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001392039998791006,
"count": 1,
"self": 0.0001392039998791006,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 460.7439498762194,
"count": 479527,
"is_parallel": true,
"self": 10.31835205521429,
"children": {
"process_trajectory": {
"total": 259.3058808840028,
"count": 479527,
"is_parallel": true,
"self": 258.57562992500243,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7302509590003865,
"count": 4,
"is_parallel": true,
"self": 0.7302509590003865
}
}
},
"_update_policy": {
"total": 191.1197169370023,
"count": 90,
"is_parallel": true,
"self": 60.47315270499371,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.6465642320086,
"count": 4587,
"is_parallel": true,
"self": 130.6465642320086
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12921061299994108,
"count": 1,
"self": 0.0010984289997395535,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12811218400020152,
"count": 1,
"self": 0.12811218400020152
}
}
}
}
}
}
}