sun-s's picture
First Push
44144a4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1376715898513794,
"min": 1.1376715898513794,
"max": 2.8539822101593018,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10887.517578125,
"min": 10887.517578125,
"max": 29227.6328125,
"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": 12.130206108093262,
"min": 0.4217175245285034,
"max": 12.130206108093262,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2365.39013671875,
"min": 81.81320190429688,
"max": 2453.62255859375,
"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": 0.07388958715583774,
"min": 0.0639365677625071,
"max": 0.07698893573183788,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29555834862335095,
"min": 0.263073294638946,
"max": 0.3692967418453419,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2203182708106789,
"min": 0.15261607926211085,
"max": 0.26408709427889654,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8812730832427156,
"min": 0.6104643170484434,
"max": 1.3204354713944828,
"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": 24.09090909090909,
"min": 3.8181818181818183,
"max": 24.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1060.0,
"min": 168.0,
"max": 1319.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.09090909090909,
"min": 3.8181818181818183,
"max": 24.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1060.0,
"min": 168.0,
"max": 1319.0,
"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": "1731241801",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731242398"
},
"total": 596.700616736,
"count": 1,
"self": 0.487165584999957,
"children": {
"run_training.setup": {
"total": 0.07480275799997571,
"count": 1,
"self": 0.07480275799997571
},
"TrainerController.start_learning": {
"total": 596.138648393,
"count": 1,
"self": 0.8488107960047273,
"children": {
"TrainerController._reset_env": {
"total": 6.205443652999975,
"count": 1,
"self": 6.205443652999975
},
"TrainerController.advance": {
"total": 588.9965303529954,
"count": 18202,
"self": 0.4222774339930311,
"children": {
"env_step": {
"total": 588.5742529190023,
"count": 18202,
"self": 452.76473196299713,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.4101335220035,
"count": 18202,
"self": 2.30930220400802,
"children": {
"TorchPolicy.evaluate": {
"total": 133.10083131799547,
"count": 18202,
"self": 133.10083131799547
}
}
},
"workers": {
"total": 0.39938743400171006,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 594.3155611209972,
"count": 18202,
"is_parallel": true,
"self": 282.2323667580007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003814362000014171,
"count": 1,
"is_parallel": true,
"self": 0.001081138999779796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002733223000234375,
"count": 10,
"is_parallel": true,
"self": 0.002733223000234375
}
}
},
"UnityEnvironment.step": {
"total": 0.05930547299999489,
"count": 1,
"is_parallel": true,
"self": 0.0007855160000076467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004849950000220815,
"count": 1,
"is_parallel": true,
"self": 0.0004849950000220815
},
"communicator.exchange": {
"total": 0.05580060199997661,
"count": 1,
"is_parallel": true,
"self": 0.05580060199997661
},
"steps_from_proto": {
"total": 0.0022343599999885555,
"count": 1,
"is_parallel": true,
"self": 0.0004268850000812563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018074749999072992,
"count": 10,
"is_parallel": true,
"self": 0.0018074749999072992
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 312.08319436299655,
"count": 18201,
"is_parallel": true,
"self": 14.604156006989456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.759254875004785,
"count": 18201,
"is_parallel": true,
"self": 7.759254875004785
},
"communicator.exchange": {
"total": 246.45697036800618,
"count": 18201,
"is_parallel": true,
"self": 246.45697036800618
},
"steps_from_proto": {
"total": 43.26281311299613,
"count": 18201,
"is_parallel": true,
"self": 8.604627761006611,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.658185351989516,
"count": 182010,
"is_parallel": true,
"self": 34.658185351989516
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018841899998278677,
"count": 1,
"self": 0.00018841899998278677,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 582.2482204879237,
"count": 771056,
"is_parallel": true,
"self": 17.14808071598418,
"children": {
"process_trajectory": {
"total": 314.38751834494013,
"count": 771056,
"is_parallel": true,
"self": 312.9572215859402,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4302967589999298,
"count": 4,
"is_parallel": true,
"self": 1.4302967589999298
}
}
},
"_update_policy": {
"total": 250.71262142699942,
"count": 90,
"is_parallel": true,
"self": 69.55029774699642,
"children": {
"TorchPPOOptimizer.update": {
"total": 181.162323680003,
"count": 4584,
"is_parallel": true,
"self": 181.162323680003
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0876751719999902,
"count": 1,
"self": 0.0011470230000441006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0865281489999461,
"count": 1,
"self": 0.0865281489999461
}
}
}
}
}
}
}