Alvaroooooooo's picture
First Push
73b00be verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7027174830436707,
"min": 0.7027174830436707,
"max": 2.8679049015045166,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6709.54638671875,
"min": 6709.54638671875,
"max": 29370.21484375,
"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": 12.750317573547363,
"min": 0.41042840480804443,
"max": 12.750317573547363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2486.31201171875,
"min": 79.62310791015625,
"max": 2588.31591796875,
"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": 0.06743036591062407,
"min": 0.06198283351053867,
"max": 0.07318693142345485,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2697214636424963,
"min": 0.2618366228536401,
"max": 0.3603084633120007,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20388610803467383,
"min": 0.12527499614539098,
"max": 0.30449027290531233,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8155444321386953,
"min": 0.5010999845815639,
"max": 1.5224513645265616,
"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": 25.204545454545453,
"min": 3.590909090909091,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 158.0,
"max": 1374.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.590909090909091,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 158.0,
"max": 1374.0,
"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": "1714676815",
"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/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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714677269"
},
"total": 453.21823928699996,
"count": 1,
"self": 0.43267105700033426,
"children": {
"run_training.setup": {
"total": 0.05748222699980943,
"count": 1,
"self": 0.05748222699980943
},
"TrainerController.start_learning": {
"total": 452.7280860029998,
"count": 1,
"self": 0.5552009469852237,
"children": {
"TrainerController._reset_env": {
"total": 2.931214399000055,
"count": 1,
"self": 2.931214399000055
},
"TrainerController.advance": {
"total": 449.13951680901437,
"count": 18198,
"self": 0.27497781299825874,
"children": {
"env_step": {
"total": 448.8645389960161,
"count": 18198,
"self": 291.4609582080159,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.11520603001418,
"count": 18198,
"self": 1.513620043994706,
"children": {
"TorchPolicy.evaluate": {
"total": 155.60158598601947,
"count": 18198,
"self": 155.60158598601947
}
}
},
"workers": {
"total": 0.2883747579860483,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 451.38413570598937,
"count": 18198,
"is_parallel": true,
"self": 225.0980544999809,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007875323999996908,
"count": 1,
"is_parallel": true,
"self": 0.0038346860001183813,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004040637999878527,
"count": 10,
"is_parallel": true,
"self": 0.004040637999878527
}
}
},
"UnityEnvironment.step": {
"total": 0.03613926000002721,
"count": 1,
"is_parallel": true,
"self": 0.0006684959998892737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040654800000083924,
"count": 1,
"is_parallel": true,
"self": 0.00040654800000083924
},
"communicator.exchange": {
"total": 0.033028929000010976,
"count": 1,
"is_parallel": true,
"self": 0.033028929000010976
},
"steps_from_proto": {
"total": 0.002035287000126118,
"count": 1,
"is_parallel": true,
"self": 0.0003866639999614563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016486230001646618,
"count": 10,
"is_parallel": true,
"self": 0.0016486230001646618
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.28608120600848,
"count": 18197,
"is_parallel": true,
"self": 10.576474543006498,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4840544200062595,
"count": 18197,
"is_parallel": true,
"self": 5.4840544200062595
},
"communicator.exchange": {
"total": 176.4421265230119,
"count": 18197,
"is_parallel": true,
"self": 176.4421265230119
},
"steps_from_proto": {
"total": 33.783425719983825,
"count": 18197,
"is_parallel": true,
"self": 6.325806403966908,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.457619316016917,
"count": 181970,
"is_parallel": true,
"self": 27.457619316016917
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012925600003654836,
"count": 1,
"self": 0.00012925600003654836,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.40467685003546,
"count": 686309,
"is_parallel": true,
"self": 14.328152063010975,
"children": {
"process_trajectory": {
"total": 246.14866694502575,
"count": 686309,
"is_parallel": true,
"self": 245.56591552702594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5827514179998161,
"count": 4,
"is_parallel": true,
"self": 0.5827514179998161
}
}
},
"_update_policy": {
"total": 182.92785784199873,
"count": 90,
"is_parallel": true,
"self": 54.81734297600906,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.11051486598967,
"count": 4587,
"is_parallel": true,
"self": 128.11051486598967
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10202459200013436,
"count": 1,
"self": 0.0009609330002149363,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10106365899991943,
"count": 1,
"self": 0.10106365899991943
}
}
}
}
}
}
}