MoBnJlal's picture
First Push
290153a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8732450008392334,
"min": 0.8558389544487,
"max": 2.8313024044036865,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8299.3203125,
"min": 8299.3203125,
"max": 28901.935546875,
"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": 13.071256637573242,
"min": 0.5328758955001831,
"max": 13.071256637573242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.89501953125,
"min": 103.37792205810547,
"max": 2642.9521484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06368913240308471,
"min": 0.06368913240308471,
"max": 0.07565041191193421,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25475652961233886,
"min": 0.25475652961233886,
"max": 0.3776861521273888,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2087489711303337,
"min": 0.15986200997505484,
"max": 0.2963342311919904,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8349958845213348,
"min": 0.6394480399002194,
"max": 1.481671155959952,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.545454545454547,
"min": 4.295454545454546,
"max": 26.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 189.0,
"max": 1453.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 4.295454545454546,
"max": 26.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 189.0,
"max": 1453.0,
"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": "1751637387",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751637819"
},
"total": 431.58148741700006,
"count": 1,
"self": 0.44006523100006234,
"children": {
"run_training.setup": {
"total": 0.02441161199999442,
"count": 1,
"self": 0.02441161199999442
},
"TrainerController.start_learning": {
"total": 431.117010574,
"count": 1,
"self": 0.35726489600074274,
"children": {
"TrainerController._reset_env": {
"total": 3.161430802000041,
"count": 1,
"self": 3.161430802000041
},
"TrainerController.advance": {
"total": 427.5153789119993,
"count": 18192,
"self": 0.39459912098482164,
"children": {
"env_step": {
"total": 307.01580269899796,
"count": 18192,
"self": 235.50819495298538,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.29128644601087,
"count": 18192,
"self": 1.2886636950165666,
"children": {
"TorchPolicy.evaluate": {
"total": 70.0026227509943,
"count": 18192,
"self": 70.0026227509943
}
}
},
"workers": {
"total": 0.21632130000170946,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 429.60783733599646,
"count": 18192,
"is_parallel": true,
"self": 222.9822295670101,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005419742000185579,
"count": 1,
"is_parallel": true,
"self": 0.0038784380003562546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015413039998293243,
"count": 10,
"is_parallel": true,
"self": 0.0015413039998293243
}
}
},
"UnityEnvironment.step": {
"total": 0.03880367300007492,
"count": 1,
"is_parallel": true,
"self": 0.0006755760000487498,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004353350000201317,
"count": 1,
"is_parallel": true,
"self": 0.0004353350000201317
},
"communicator.exchange": {
"total": 0.035691246999931536,
"count": 1,
"is_parallel": true,
"self": 0.035691246999931536
},
"steps_from_proto": {
"total": 0.0020015150000745052,
"count": 1,
"is_parallel": true,
"self": 0.00039564400003655464,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016058710000379506,
"count": 10,
"is_parallel": true,
"self": 0.0016058710000379506
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.62560776898636,
"count": 18191,
"is_parallel": true,
"self": 9.981869594992986,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.544947410012583,
"count": 18191,
"is_parallel": true,
"self": 5.544947410012583
},
"communicator.exchange": {
"total": 158.67024586098842,
"count": 18191,
"is_parallel": true,
"self": 158.67024586098842
},
"steps_from_proto": {
"total": 32.42854490299237,
"count": 18191,
"is_parallel": true,
"self": 5.794197547020758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.634347355971613,
"count": 181910,
"is_parallel": true,
"self": 26.634347355971613
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.1049770920165,
"count": 18192,
"self": 0.45539755702452567,
"children": {
"process_trajectory": {
"total": 26.536570632991697,
"count": 18192,
"self": 26.09786670599192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43870392699977856,
"count": 4,
"self": 0.43870392699977856
}
}
},
"_update_policy": {
"total": 93.11300890200027,
"count": 90,
"self": 38.77518893399565,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.337819968004624,
"count": 4587,
"self": 54.337819968004624
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.559998943586834e-07,
"count": 1,
"self": 9.559998943586834e-07
},
"TrainerController._save_models": {
"total": 0.08293500800004949,
"count": 1,
"self": 0.0008760630000779202,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08205894499997157,
"count": 1,
"self": 0.08205894499997157
}
}
}
}
}
}
}