paulmerceur's picture
First Push
800ea30 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7845714688301086,
"min": 0.77692049741745,
"max": 2.8611018657684326,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7456.5673828125,
"min": 7456.5673828125,
"max": 29206.12890625,
"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": 13.024835586547852,
"min": 0.3492893874645233,
"max": 13.024835586547852,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2539.843017578125,
"min": 67.76213836669922,
"max": 2650.392578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06930083803394263,
"min": 0.06442245578235836,
"max": 0.07652981732732286,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2772033521357705,
"min": 0.2663385616421389,
"max": 0.38264908663661434,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2315464284197957,
"min": 0.11262375791328869,
"max": 0.29429595265902725,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9261857136791828,
"min": 0.45049503165315474,
"max": 1.4714797632951362,
"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": 25.613636363636363,
"min": 3.2045454545454546,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 141.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.2045454545454546,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 141.0,
"max": 1406.0,
"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": "1752600487",
"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": "1752601104"
},
"total": 616.8841731530001,
"count": 1,
"self": 0.6932709020004495,
"children": {
"run_training.setup": {
"total": 0.04346738999993249,
"count": 1,
"self": 0.04346738999993249
},
"TrainerController.start_learning": {
"total": 616.1474348609997,
"count": 1,
"self": 0.7297461820282933,
"children": {
"TrainerController._reset_env": {
"total": 4.954911688000038,
"count": 1,
"self": 4.954911688000038
},
"TrainerController.advance": {
"total": 610.3833500879716,
"count": 18192,
"self": 0.7376164290042198,
"children": {
"env_step": {
"total": 431.44324243299866,
"count": 18192,
"self": 369.32749343101614,
"children": {
"SubprocessEnvManager._take_step": {
"total": 61.68260765199875,
"count": 18192,
"self": 2.2608094320044074,
"children": {
"TorchPolicy.evaluate": {
"total": 59.42179821999434,
"count": 18192,
"self": 59.42179821999434
}
}
},
"workers": {
"total": 0.43314134998377085,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 613.5371664359768,
"count": 18192,
"is_parallel": true,
"self": 296.2841527469741,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008671722000144655,
"count": 1,
"is_parallel": true,
"self": 0.006070438999813632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026012830003310228,
"count": 10,
"is_parallel": true,
"self": 0.0026012830003310228
}
}
},
"UnityEnvironment.step": {
"total": 0.07594196099989858,
"count": 1,
"is_parallel": true,
"self": 0.0007285899998805689,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004584119999435643,
"count": 1,
"is_parallel": true,
"self": 0.0004584119999435643
},
"communicator.exchange": {
"total": 0.07277783199992882,
"count": 1,
"is_parallel": true,
"self": 0.07277783199992882
},
"steps_from_proto": {
"total": 0.0019771270001456287,
"count": 1,
"is_parallel": true,
"self": 0.0004204460003620625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015566809997835662,
"count": 10,
"is_parallel": true,
"self": 0.0015566809997835662
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 317.2530136890027,
"count": 18191,
"is_parallel": true,
"self": 15.50859523898771,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.29163841299237,
"count": 18191,
"is_parallel": true,
"self": 8.29163841299237
},
"communicator.exchange": {
"total": 248.3552326729955,
"count": 18191,
"is_parallel": true,
"self": 248.3552326729955
},
"steps_from_proto": {
"total": 45.09754736402715,
"count": 18191,
"is_parallel": true,
"self": 8.983849748072316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.113697615954834,
"count": 181910,
"is_parallel": true,
"self": 36.113697615954834
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 178.20249122596874,
"count": 18192,
"self": 1.0049093649593033,
"children": {
"process_trajectory": {
"total": 33.5036152720088,
"count": 18192,
"self": 33.076758103008615,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42685716900018633,
"count": 4,
"self": 0.42685716900018633
}
}
},
"_update_policy": {
"total": 143.69396658900064,
"count": 90,
"self": 53.75458103599658,
"children": {
"TorchPPOOptimizer.update": {
"total": 89.93938555300406,
"count": 4587,
"self": 89.93938555300406
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0069998097606003e-06,
"count": 1,
"self": 1.0069998097606003e-06
},
"TrainerController._save_models": {
"total": 0.07942589599997518,
"count": 1,
"self": 0.00137387899985697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07805201700011821,
"count": 1,
"self": 0.07805201700011821
}
}
}
}
}
}
}