celocho's picture
First Push
683707e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.8568007946014404,
"min": 2.8568007946014404,
"max": 2.8892247676849365,
"count": 2
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 27402.43359375,
"min": 27402.43359375,
"max": 29493.20703125,
"count": 2
},
"SnowballTarget.Step.mean": {
"value": 19984.0,
"min": 9952.0,
"max": 19984.0,
"count": 2
},
"SnowballTarget.Step.sum": {
"value": 19984.0,
"min": 9952.0,
"max": 19984.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.515291154384613,
"min": 0.13076090812683105,
"max": 0.515291154384613,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 52.55970001220703,
"min": 12.422286033630371,
"max": 52.55970001220703,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 2
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 3.4444444444444446,
"min": 3.227272727272727,
"max": 3.4444444444444446,
"count": 2
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 186.0,
"min": 142.0,
"max": 186.0,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 3.4444444444444446,
"min": 3.227272727272727,
"max": 3.4444444444444446,
"count": 2
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 186.0,
"min": 142.0,
"max": 186.0,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.032652815368692245,
"min": 0.032652815368692245,
"max": 0.032889401037664356,
"count": 2
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06530563073738449,
"min": 0.06530563073738449,
"max": 0.06577880207532871,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.125598820974119,
"min": 0.12147390993777663,
"max": 0.125598820974119,
"count": 2
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.251197641948238,
"min": 0.24294781987555325,
"max": 0.251197641948238,
"count": 2
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 9.4781338552e-05,
"min": 9.4781338552e-05,
"max": 9.7714668952e-05,
"count": 2
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.000189562677104,
"min": 0.000189562677104,
"max": 0.000195429337904,
"count": 2
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.19478133333333333,
"min": 0.19478133333333333,
"max": 0.19771466666666668,
"count": 2
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.38956266666666667,
"min": 0.38956266666666667,
"max": 0.39542933333333335,
"count": 2
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0047395885333333335,
"min": 0.0047395885333333335,
"max": 0.004885961866666667,
"count": 2
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.009479177066666667,
"min": 0.009479177066666667,
"max": 0.009771923733333333,
"count": 2
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1734345440",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734345503"
},
"total": 63.05687432700006,
"count": 1,
"self": 0.165197862000241,
"children": {
"run_training.setup": {
"total": 0.053642877000129374,
"count": 1,
"self": 0.053642877000129374
},
"TrainerController.start_learning": {
"total": 62.83803358799969,
"count": 1,
"self": 0.05968189500572407,
"children": {
"TrainerController._reset_env": {
"total": 1.8741869640002733,
"count": 1,
"self": 1.8741869640002733
},
"TrainerController.advance": {
"total": 60.5440248019936,
"count": 2595,
"self": 0.06128617002195824,
"children": {
"env_step": {
"total": 45.24623885799565,
"count": 2595,
"self": 34.371922099990115,
"children": {
"SubprocessEnvManager._take_step": {
"total": 10.840280149015143,
"count": 2595,
"self": 0.1930087980153985,
"children": {
"TorchPolicy.evaluate": {
"total": 10.647271350999745,
"count": 2595,
"self": 10.647271350999745
}
}
},
"workers": {
"total": 0.03403660899039096,
"count": 2594,
"self": 0.0,
"children": {
"worker_root": {
"total": 62.328322223013856,
"count": 2594,
"is_parallel": true,
"self": 32.35301709001624,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002056752000044071,
"count": 1,
"is_parallel": true,
"self": 0.0006673490001958271,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013894029998482438,
"count": 10,
"is_parallel": true,
"self": 0.0013894029998482438
}
}
},
"UnityEnvironment.step": {
"total": 0.03538853600002767,
"count": 1,
"is_parallel": true,
"self": 0.000591672999689763,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003957849999096652,
"count": 1,
"is_parallel": true,
"self": 0.0003957849999096652
},
"communicator.exchange": {
"total": 0.03254683000022851,
"count": 1,
"is_parallel": true,
"self": 0.03254683000022851
},
"steps_from_proto": {
"total": 0.001854248000199732,
"count": 1,
"is_parallel": true,
"self": 0.0003865670005325228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001467680999667209,
"count": 10,
"is_parallel": true,
"self": 0.001467680999667209
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 29.97530513299762,
"count": 2593,
"is_parallel": true,
"self": 1.426354452978103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.7860832880146518,
"count": 2593,
"is_parallel": true,
"self": 0.7860832880146518
},
"communicator.exchange": {
"total": 23.094042740007808,
"count": 2593,
"is_parallel": true,
"self": 23.094042740007808
},
"steps_from_proto": {
"total": 4.668824651997056,
"count": 2593,
"is_parallel": true,
"self": 0.8578550389456723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.810969613051384,
"count": 25930,
"is_parallel": true,
"self": 3.810969613051384
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 15.236499773975993,
"count": 2594,
"self": 0.0796725699660783,
"children": {
"process_trajectory": {
"total": 3.0663161460101946,
"count": 2594,
"self": 3.0663161460101946
},
"_update_policy": {
"total": 12.09051105799972,
"count": 6,
"self": 7.561024990001442,
"children": {
"TorchPPOOptimizer.update": {
"total": 4.529486067998278,
"count": 192,
"self": 4.529486067998278
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.666000116529176e-06,
"count": 1,
"self": 1.666000116529176e-06
},
"TrainerController._save_models": {
"total": 0.3601382609999746,
"count": 1,
"self": 0.007063416999699257,
"children": {
"RLTrainer._checkpoint": {
"total": 0.35307484400027533,
"count": 1,
"self": 0.35307484400027533
}
}
}
}
}
}
}