graceneutrality's picture
First Push
94fc3c0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8355351090431213,
"min": 0.8355351090431213,
"max": 2.8719966411590576,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7986.88037109375,
"min": 7986.88037109375,
"max": 29412.1171875,
"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": 12.921995162963867,
"min": 0.4698830842971802,
"max": 12.921995162963867,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.7890625,
"min": 91.15731811523438,
"max": 2645.876953125,
"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": 0.06787784635939627,
"min": 0.06267652268705241,
"max": 0.07843445403719385,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2715113854375851,
"min": 0.25070609074820965,
"max": 0.3752899937817882,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18947761104095215,
"min": 0.11625233777757624,
"max": 0.30416062846779823,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7579104441638086,
"min": 0.46500935111030495,
"max": 1.4840961708230715,
"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": 25.704545454545453,
"min": 3.340909090909091,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 147.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.340909090909091,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 147.0,
"max": 1389.0,
"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": "1706232528",
"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. --force --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706232991"
},
"total": 462.364742019,
"count": 1,
"self": 0.42524368400063395,
"children": {
"run_training.setup": {
"total": 0.06931752899981802,
"count": 1,
"self": 0.06931752899981802
},
"TrainerController.start_learning": {
"total": 461.87018080599955,
"count": 1,
"self": 0.5624284509822246,
"children": {
"TrainerController._reset_env": {
"total": 2.335377590000462,
"count": 1,
"self": 2.335377590000462
},
"TrainerController.advance": {
"total": 458.87573395401705,
"count": 18200,
"self": 0.28206531695559534,
"children": {
"env_step": {
"total": 458.59366863706146,
"count": 18200,
"self": 295.9570193770687,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.3415395640468,
"count": 18200,
"self": 1.5232037590549226,
"children": {
"TorchPolicy.evaluate": {
"total": 160.81833580499188,
"count": 18200,
"self": 160.81833580499188
}
}
},
"workers": {
"total": 0.29510969594593917,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.72020179501305,
"count": 18200,
"is_parallel": true,
"self": 228.6589457739783,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001973370999621693,
"count": 1,
"is_parallel": true,
"self": 0.0005347039987100288,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014386670009116642,
"count": 10,
"is_parallel": true,
"self": 0.0014386670009116642
}
}
},
"UnityEnvironment.step": {
"total": 0.0749143279999771,
"count": 1,
"is_parallel": true,
"self": 0.0006942990003153682,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003760109993891092,
"count": 1,
"is_parallel": true,
"self": 0.0003760109993891092
},
"communicator.exchange": {
"total": 0.07192866500008677,
"count": 1,
"is_parallel": true,
"self": 0.07192866500008677
},
"steps_from_proto": {
"total": 0.0019153530001858599,
"count": 1,
"is_parallel": true,
"self": 0.0003367769995747949,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001578576000611065,
"count": 10,
"is_parallel": true,
"self": 0.001578576000611065
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.06125602103475,
"count": 18199,
"is_parallel": true,
"self": 11.118393423986163,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.768811309992998,
"count": 18199,
"is_parallel": true,
"self": 5.768811309992998
},
"communicator.exchange": {
"total": 178.80229501803115,
"count": 18199,
"is_parallel": true,
"self": 178.80229501803115
},
"steps_from_proto": {
"total": 36.371756269024445,
"count": 18199,
"is_parallel": true,
"self": 6.667596664036864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.70415960498758,
"count": 181990,
"is_parallel": true,
"self": 29.70415960498758
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.0330000047106296e-05,
"count": 1,
"self": 4.0330000047106296e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.623087587006,
"count": 688869,
"is_parallel": true,
"self": 15.657560275359174,
"children": {
"process_trajectory": {
"total": 250.59211964164933,
"count": 688869,
"is_parallel": true,
"self": 249.9198626706493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6722569710000244,
"count": 4,
"is_parallel": true,
"self": 0.6722569710000244
}
}
},
"_update_policy": {
"total": 186.3734076699975,
"count": 90,
"is_parallel": true,
"self": 53.947440217014446,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.42596745298306,
"count": 4584,
"is_parallel": true,
"self": 132.42596745298306
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09660048099976848,
"count": 1,
"self": 0.0012012519991912995,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09539922900057718,
"count": 1,
"self": 0.09539922900057718
}
}
}
}
}
}
}