Megalino111's picture
First Push
5a6e6ad verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7965793013572693,
"min": 0.7965793013572693,
"max": 2.861267328262329,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7605.7392578125,
"min": 7605.7392578125,
"max": 29333.712890625,
"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": 13.157942771911621,
"min": 0.4909791052341461,
"max": 13.157942771911621,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.798828125,
"min": 95.24994659423828,
"max": 2652.36474609375,
"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": 0.07365348233254147,
"min": 0.062463727970252333,
"max": 0.07365348233254147,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2946139293301659,
"min": 0.24985491188100933,
"max": 0.35580952290740026,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18339906156282212,
"min": 0.11749263923967887,
"max": 0.2594315111637115,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7335962462512885,
"min": 0.4699705569587155,
"max": 1.2971575558185575,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382800001,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.863636363636363,
"min": 3.4318181818181817,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 151.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.4318181818181817,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 151.0,
"max": 1435.0,
"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": "1711814671",
"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=SnowballTarget_2 --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": "1711815177"
},
"total": 505.92118633599966,
"count": 1,
"self": 0.478293470999688,
"children": {
"run_training.setup": {
"total": 0.0508603180001046,
"count": 1,
"self": 0.0508603180001046
},
"TrainerController.start_learning": {
"total": 505.39203254699987,
"count": 1,
"self": 0.5827457259888433,
"children": {
"TrainerController._reset_env": {
"total": 1.9353972330000033,
"count": 1,
"self": 1.9353972330000033
},
"TrainerController.advance": {
"total": 502.7830070160112,
"count": 18199,
"self": 0.289797671955057,
"children": {
"env_step": {
"total": 502.49320934405614,
"count": 18199,
"self": 334.5084811870879,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.68619183196734,
"count": 18199,
"self": 1.5793524900013836,
"children": {
"TorchPolicy.evaluate": {
"total": 166.10683934196595,
"count": 18199,
"self": 166.10683934196595
}
}
},
"workers": {
"total": 0.2985363250008959,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 504.14980582205226,
"count": 18199,
"is_parallel": true,
"self": 269.17307836503824,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023864780000621977,
"count": 1,
"is_parallel": true,
"self": 0.0007074210011523974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016790569989098003,
"count": 10,
"is_parallel": true,
"self": 0.0016790569989098003
}
}
},
"UnityEnvironment.step": {
"total": 0.039732972999900085,
"count": 1,
"is_parallel": true,
"self": 0.0007441459997608035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040609600000607315,
"count": 1,
"is_parallel": true,
"self": 0.00040609600000607315
},
"communicator.exchange": {
"total": 0.03622750400018049,
"count": 1,
"is_parallel": true,
"self": 0.03622750400018049
},
"steps_from_proto": {
"total": 0.0023552269999527198,
"count": 1,
"is_parallel": true,
"self": 0.0004313509998610243,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019238760000916955,
"count": 10,
"is_parallel": true,
"self": 0.0019238760000916955
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.97672745701402,
"count": 18198,
"is_parallel": true,
"self": 10.844048338034554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.8218318570225165,
"count": 18198,
"is_parallel": true,
"self": 5.8218318570225165
},
"communicator.exchange": {
"total": 181.59153125093917,
"count": 18198,
"is_parallel": true,
"self": 181.59153125093917
},
"steps_from_proto": {
"total": 36.71931601101778,
"count": 18198,
"is_parallel": true,
"self": 6.885056439073196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.834259571944585,
"count": 181980,
"is_parallel": true,
"self": 29.834259571944585
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014016399973115767,
"count": 1,
"self": 0.00014016399973115767,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 496.4783875168664,
"count": 700008,
"is_parallel": true,
"self": 16.220282634042178,
"children": {
"process_trajectory": {
"total": 257.3785882338234,
"count": 700008,
"is_parallel": true,
"self": 256.83755923482295,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5410289990004458,
"count": 4,
"is_parallel": true,
"self": 0.5410289990004458
}
}
},
"_update_policy": {
"total": 222.87951664900083,
"count": 90,
"is_parallel": true,
"self": 68.06298923500799,
"children": {
"TorchPPOOptimizer.update": {
"total": 154.81652741399284,
"count": 6116,
"is_parallel": true,
"self": 154.81652741399284
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09074240800009648,
"count": 1,
"self": 0.001034858000366512,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08970754999972996,
"count": 1,
"self": 0.08970754999972996
}
}
}
}
}
}
}