furkanbicer's picture
First Push
bc0d63c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1315618753433228,
"min": 1.1315618753433228,
"max": 2.861271381378174,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10791.7060546875,
"min": 10791.7060546875,
"max": 29302.28125,
"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": 12.51957893371582,
"min": 0.31432297825813293,
"max": 12.51957893371582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2441.31787109375,
"min": 60.978660583496094,
"max": 2511.39306640625,
"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": 0.06637017348268773,
"min": 0.06271711037120173,
"max": 0.08021426545079414,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2654806939307509,
"min": 0.2508684414848069,
"max": 0.4010713272539707,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1979481569107841,
"min": 0.10356481062298568,
"max": 0.2799604662200984,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7917926276431364,
"min": 0.41425924249194274,
"max": 1.2904713183057073,
"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": 25.09090909090909,
"min": 3.022727272727273,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 133.0,
"max": 1359.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.022727272727273,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 133.0,
"max": 1359.0,
"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": "1716964150",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716964606"
},
"total": 456.0033701950001,
"count": 1,
"self": 0.3858012939999753,
"children": {
"run_training.setup": {
"total": 0.05349461100013286,
"count": 1,
"self": 0.05349461100013286
},
"TrainerController.start_learning": {
"total": 455.56407429,
"count": 1,
"self": 0.565706017973298,
"children": {
"TrainerController._reset_env": {
"total": 2.65263642500031,
"count": 1,
"self": 2.65263642500031
},
"TrainerController.advance": {
"total": 452.25352039802647,
"count": 18200,
"self": 0.29757473201789253,
"children": {
"env_step": {
"total": 451.9559456660086,
"count": 18200,
"self": 294.46609945502496,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.20084053799064,
"count": 18200,
"self": 1.470547536990125,
"children": {
"TorchPolicy.evaluate": {
"total": 155.73029300100052,
"count": 18200,
"self": 155.73029300100052
}
}
},
"workers": {
"total": 0.2890056729929711,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.3701877839794,
"count": 18200,
"is_parallel": true,
"self": 228.76360478799734,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002350601999751234,
"count": 1,
"is_parallel": true,
"self": 0.0006691639991913689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001681438000559865,
"count": 10,
"is_parallel": true,
"self": 0.001681438000559865
}
}
},
"UnityEnvironment.step": {
"total": 0.07612489099983577,
"count": 1,
"is_parallel": true,
"self": 0.000744074000067485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042036500008180155,
"count": 1,
"is_parallel": true,
"self": 0.00042036500008180155
},
"communicator.exchange": {
"total": 0.07279363099996772,
"count": 1,
"is_parallel": true,
"self": 0.07279363099996772
},
"steps_from_proto": {
"total": 0.002166820999718766,
"count": 1,
"is_parallel": true,
"self": 0.0004554349998215912,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017113859998971748,
"count": 10,
"is_parallel": true,
"self": 0.0017113859998971748
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.60658299598208,
"count": 18199,
"is_parallel": true,
"self": 10.239995130988973,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.473785937002958,
"count": 18199,
"is_parallel": true,
"self": 5.473785937002958
},
"communicator.exchange": {
"total": 175.3788051310239,
"count": 18199,
"is_parallel": true,
"self": 175.3788051310239
},
"steps_from_proto": {
"total": 34.51399679696624,
"count": 18199,
"is_parallel": true,
"self": 6.560627837960055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.953368959006184,
"count": 181990,
"is_parallel": true,
"self": 27.953368959006184
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012882800001534633,
"count": 1,
"self": 0.00012882800001534633,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.6090162599021,
"count": 661536,
"is_parallel": true,
"self": 14.133034990958095,
"children": {
"process_trajectory": {
"total": 247.90940510294604,
"count": 661536,
"is_parallel": true,
"self": 247.0560277279451,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8533773750009459,
"count": 4,
"is_parallel": true,
"self": 0.8533773750009459
}
}
},
"_update_policy": {
"total": 184.56657616599796,
"count": 90,
"is_parallel": true,
"self": 57.48404899199795,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.082527174,
"count": 4587,
"is_parallel": true,
"self": 127.082527174
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09208262099991771,
"count": 1,
"self": 0.0008912910002436547,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09119132999967405,
"count": 1,
"self": 0.09119132999967405
}
}
}
}
}
}
}