togu6669's picture
First Push
51176ff verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9257403612136841,
"min": 0.8226544260978699,
"max": 2.819223165512085,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8798.236328125,
"min": 8044.8837890625,
"max": 28778.62890625,
"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": 12.80591869354248,
"min": 0.47970810532569885,
"max": 12.80591869354248,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.154052734375,
"min": 93.06336975097656,
"max": 2590.23095703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07588236564329326,
"min": 0.06318104818523816,
"max": 0.07588236564329326,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30352946257317304,
"min": 0.25272419274095265,
"max": 0.3764640102676554,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2273254344860713,
"min": 0.14882755379521234,
"max": 0.2847064262511683,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9093017379442851,
"min": 0.5953102151808494,
"max": 1.4235321312558415,
"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": 25.25,
"min": 4.045454545454546,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 178.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 4.045454545454546,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 178.0,
"max": 1416.0,
"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": "1741552658",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741553069"
},
"total": 411.1859639700001,
"count": 1,
"self": 0.8066700880001463,
"children": {
"run_training.setup": {
"total": 0.022785786999975244,
"count": 1,
"self": 0.022785786999975244
},
"TrainerController.start_learning": {
"total": 410.356508095,
"count": 1,
"self": 0.31280908999588064,
"children": {
"TrainerController._reset_env": {
"total": 3.0440126690000398,
"count": 1,
"self": 3.0440126690000398
},
"TrainerController.advance": {
"total": 406.86524607700426,
"count": 18192,
"self": 0.3529171460204452,
"children": {
"env_step": {
"total": 287.4448846929972,
"count": 18192,
"self": 219.30715773999646,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.94666285899984,
"count": 18192,
"self": 1.183028189997458,
"children": {
"TorchPolicy.evaluate": {
"total": 66.76363466900239,
"count": 18192,
"self": 66.76363466900239
}
}
},
"workers": {
"total": 0.1910640940009216,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 408.7384050830117,
"count": 18192,
"is_parallel": true,
"self": 215.90751057604052,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005557242000122642,
"count": 1,
"is_parallel": true,
"self": 0.004008524999790097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015487170003325446,
"count": 10,
"is_parallel": true,
"self": 0.0015487170003325446
}
}
},
"UnityEnvironment.step": {
"total": 0.0352605789998961,
"count": 1,
"is_parallel": true,
"self": 0.0005855229999269795,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043358700008866435,
"count": 1,
"is_parallel": true,
"self": 0.00043358700008866435
},
"communicator.exchange": {
"total": 0.032459115999927235,
"count": 1,
"is_parallel": true,
"self": 0.032459115999927235
},
"steps_from_proto": {
"total": 0.0017823529999532184,
"count": 1,
"is_parallel": true,
"self": 0.00035499499995239603,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014273580000008224,
"count": 10,
"is_parallel": true,
"self": 0.0014273580000008224
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.83089450697116,
"count": 18191,
"is_parallel": true,
"self": 9.585960139960434,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2641173089944004,
"count": 18191,
"is_parallel": true,
"self": 5.2641173089944004
},
"communicator.exchange": {
"total": 147.87030350900136,
"count": 18191,
"is_parallel": true,
"self": 147.87030350900136
},
"steps_from_proto": {
"total": 30.110513549014968,
"count": 18191,
"is_parallel": true,
"self": 5.2753125860310774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.83520096298389,
"count": 181910,
"is_parallel": true,
"self": 24.83520096298389
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.06744423798659,
"count": 18192,
"self": 0.3713133259714141,
"children": {
"process_trajectory": {
"total": 25.986851202015032,
"count": 18192,
"self": 25.41070719201548,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5761440099995525,
"count": 4,
"self": 0.5761440099995525
}
}
},
"_update_policy": {
"total": 92.70927971000015,
"count": 90,
"self": 37.01114574399139,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.698133966008754,
"count": 4587,
"self": 55.698133966008754
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4909999208612135e-06,
"count": 1,
"self": 1.4909999208612135e-06
},
"TrainerController._save_models": {
"total": 0.13443876799988175,
"count": 1,
"self": 0.0012043099998209073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13323445800006084,
"count": 1,
"self": 0.13323445800006084
}
}
}
}
}
}
}