magjico's picture
First Push
896e529 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.870115339756012,
"min": 0.870115339756012,
"max": 2.8553061485290527,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8307.861328125,
"min": 8307.861328125,
"max": 29241.189453125,
"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": 12.844966888427734,
"min": 0.5529496073722839,
"max": 12.848937034606934,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.7685546875,
"min": 107.27222442626953,
"max": 2621.18310546875,
"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": 0.06819341888916039,
"min": 0.06172073353795271,
"max": 0.07344170213835632,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27277367555664156,
"min": 0.24688293415181084,
"max": 0.3644378792905984,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19943755222301857,
"min": 0.14880925291857006,
"max": 0.2947418900097118,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7977502088920743,
"min": 0.5952370116742802,
"max": 1.473709450048559,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0776097306000005e-05,
"min": 1.0776097306000005e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.310438922400002e-05,
"min": 4.310438922400002e-05,
"max": 0.0018468800382800002,
"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": 4.295454545454546,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 189.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 4.295454545454546,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 189.0,
"max": 1397.0,
"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": "1711548135",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711548568"
},
"total": 433.84229899599995,
"count": 1,
"self": 0.4934363569998368,
"children": {
"run_training.setup": {
"total": 0.0572959720000199,
"count": 1,
"self": 0.0572959720000199
},
"TrainerController.start_learning": {
"total": 433.2915666670001,
"count": 1,
"self": 0.5477438619966506,
"children": {
"TrainerController._reset_env": {
"total": 3.31574740699989,
"count": 1,
"self": 3.31574740699989
},
"TrainerController.advance": {
"total": 429.3238331030036,
"count": 18199,
"self": 0.2513800249964788,
"children": {
"env_step": {
"total": 429.07245307800713,
"count": 18199,
"self": 274.24581079102745,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.5616547029938,
"count": 18199,
"self": 1.4188852690035674,
"children": {
"TorchPolicy.evaluate": {
"total": 153.14276943399022,
"count": 18199,
"self": 153.14276943399022
}
}
},
"workers": {
"total": 0.26498758398588507,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 432.1819620520132,
"count": 18199,
"is_parallel": true,
"self": 217.79249266399825,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007814961999883963,
"count": 1,
"is_parallel": true,
"self": 0.003633221999507441,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0041817400003765215,
"count": 10,
"is_parallel": true,
"self": 0.0041817400003765215
}
}
},
"UnityEnvironment.step": {
"total": 0.03677524799991261,
"count": 1,
"is_parallel": true,
"self": 0.0006815090000600321,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040970400004880503,
"count": 1,
"is_parallel": true,
"self": 0.00040970400004880503
},
"communicator.exchange": {
"total": 0.03367988399986643,
"count": 1,
"is_parallel": true,
"self": 0.03367988399986643
},
"steps_from_proto": {
"total": 0.0020041509999373375,
"count": 1,
"is_parallel": true,
"self": 0.0004201650003778923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015839859995594452,
"count": 10,
"is_parallel": true,
"self": 0.0015839859995594452
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.38946938801496,
"count": 18198,
"is_parallel": true,
"self": 9.967439936006258,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.168856597989588,
"count": 18198,
"is_parallel": true,
"self": 5.168856597989588
},
"communicator.exchange": {
"total": 166.81595749799635,
"count": 18198,
"is_parallel": true,
"self": 166.81595749799635
},
"steps_from_proto": {
"total": 32.43721535602276,
"count": 18198,
"is_parallel": true,
"self": 5.978466685091007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.458748670931755,
"count": 181980,
"is_parallel": true,
"self": 26.458748670931755
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020134600003984815,
"count": 1,
"self": 0.00020134600003984815,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 424.1844328268942,
"count": 623015,
"is_parallel": true,
"self": 14.312715944995944,
"children": {
"process_trajectory": {
"total": 232.6232733958991,
"count": 623015,
"is_parallel": true,
"self": 232.00841864289896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6148547530001451,
"count": 4,
"is_parallel": true,
"self": 0.6148547530001451
}
}
},
"_update_policy": {
"total": 177.24844348599913,
"count": 90,
"is_parallel": true,
"self": 48.99923601800242,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.2492074679967,
"count": 4587,
"is_parallel": true,
"self": 128.2492074679967
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10404094899990923,
"count": 1,
"self": 0.0011155449997204414,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10292540400018879,
"count": 1,
"self": 0.10292540400018879
}
}
}
}
}
}
}