archishin's picture
First Push
23b72d6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8512437343597412,
"min": 0.8512437343597412,
"max": 2.865936279296875,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8090.22021484375,
"min": 8090.22021484375,
"max": 29255.4765625,
"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": 13.194785118103027,
"min": 0.47164925932884216,
"max": 13.194785118103027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2572.983154296875,
"min": 91.49995422363281,
"max": 2678.8994140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06509741404214783,
"min": 0.06258519504240659,
"max": 0.07570367676808554,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26038965616859133,
"min": 0.25327699759052885,
"max": 0.3785183838404277,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20806446452351177,
"min": 0.11689348283392723,
"max": 0.2884235902159822,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8322578580940471,
"min": 0.4675739313357089,
"max": 1.3992724704976174,
"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": 3.409090909090909,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 150.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.409090909090909,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 150.0,
"max": 1425.0,
"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": "1750395896",
"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": "1750396324"
},
"total": 428.3078696319999,
"count": 1,
"self": 0.49426288199992996,
"children": {
"run_training.setup": {
"total": 0.029093794999994316,
"count": 1,
"self": 0.029093794999994316
},
"TrainerController.start_learning": {
"total": 427.78451295499997,
"count": 1,
"self": 0.37391231900221555,
"children": {
"TrainerController._reset_env": {
"total": 3.3566298829999823,
"count": 1,
"self": 3.3566298829999823
},
"TrainerController.advance": {
"total": 423.9747820059978,
"count": 18192,
"self": 0.400877643000058,
"children": {
"env_step": {
"total": 305.90602061100094,
"count": 18192,
"self": 235.86850403299752,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.82481503399879,
"count": 18192,
"self": 1.244563533997848,
"children": {
"TorchPolicy.evaluate": {
"total": 68.58025150000094,
"count": 18192,
"self": 68.58025150000094
}
}
},
"workers": {
"total": 0.2127015440046307,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.4224152250034,
"count": 18192,
"is_parallel": true,
"self": 218.82990899300341,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006216171999994913,
"count": 1,
"is_parallel": true,
"self": 0.004760322999800337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014558490001945756,
"count": 10,
"is_parallel": true,
"self": 0.0014558490001945756
}
}
},
"UnityEnvironment.step": {
"total": 0.035527636999972856,
"count": 1,
"is_parallel": true,
"self": 0.0005608929998288659,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037119200010238274,
"count": 1,
"is_parallel": true,
"self": 0.00037119200010238274
},
"communicator.exchange": {
"total": 0.03268935400001283,
"count": 1,
"is_parallel": true,
"self": 0.03268935400001283
},
"steps_from_proto": {
"total": 0.0019061980000287804,
"count": 1,
"is_parallel": true,
"self": 0.00036576999991666526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015404280001121151,
"count": 10,
"is_parallel": true,
"self": 0.0015404280001121151
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.592506232,
"count": 18191,
"is_parallel": true,
"self": 9.793152844982501,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.321796729005769,
"count": 18191,
"is_parallel": true,
"self": 5.321796729005769
},
"communicator.exchange": {
"total": 160.69313807800688,
"count": 18191,
"is_parallel": true,
"self": 160.69313807800688
},
"steps_from_proto": {
"total": 31.784418580004854,
"count": 18191,
"is_parallel": true,
"self": 5.695628225000064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.08879035500479,
"count": 181910,
"is_parallel": true,
"self": 26.08879035500479
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.66788375199678,
"count": 18192,
"self": 0.4856485070030203,
"children": {
"process_trajectory": {
"total": 25.68452613599402,
"count": 18192,
"self": 25.260449770994114,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4240763649999053,
"count": 4,
"self": 0.4240763649999053
}
}
},
"_update_policy": {
"total": 91.49770910899974,
"count": 90,
"self": 37.626669431001574,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.87103967799817,
"count": 4587,
"self": 53.87103967799817
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0160000556425075e-06,
"count": 1,
"self": 1.0160000556425075e-06
},
"TrainerController._save_models": {
"total": 0.07918773099993359,
"count": 1,
"self": 0.0008416269998861026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07834610400004749,
"count": 1,
"self": 0.07834610400004749
}
}
}
}
}
}
}