LukeSajkowski's picture
First training
87dd377
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9614333510398865,
"min": 0.9614333510398865,
"max": 2.874887228012085,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9179.765625,
"min": 9179.765625,
"max": 29441.720703125,
"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": 12.36133861541748,
"min": 0.19347845017910004,
"max": 12.36133861541748,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2410.4609375,
"min": 37.534820556640625,
"max": 2508.48583984375,
"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": 0.06956106368577857,
"min": 0.06243040631314073,
"max": 0.0743451297372196,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27824425474311426,
"min": 0.24972162525256292,
"max": 0.37172564868609803,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20904475947221118,
"min": 0.10205633318515074,
"max": 0.28797634048204795,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8361790378888447,
"min": 0.40822533274060296,
"max": 1.3825705629937788,
"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.CumulativeReward.mean": {
"value": 24.977272727272727,
"min": 2.772727272727273,
"max": 24.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1099.0,
"min": 122.0,
"max": 1333.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.977272727272727,
"min": 2.772727272727273,
"max": 24.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1099.0,
"min": 122.0,
"max": 1333.0,
"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": "1673902029",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673902470"
},
"total": 440.68935209099993,
"count": 1,
"self": 0.39391337199992904,
"children": {
"run_training.setup": {
"total": 0.12325230499999407,
"count": 1,
"self": 0.12325230499999407
},
"TrainerController.start_learning": {
"total": 440.172186414,
"count": 1,
"self": 0.511375070001975,
"children": {
"TrainerController._reset_env": {
"total": 10.307725519000002,
"count": 1,
"self": 10.307725519000002
},
"TrainerController.advance": {
"total": 429.23211952399805,
"count": 18201,
"self": 0.28577754999793115,
"children": {
"env_step": {
"total": 428.9463419740001,
"count": 18201,
"self": 277.64975325299304,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.03352604800247,
"count": 18201,
"self": 1.518368269005066,
"children": {
"TorchPolicy.evaluate": {
"total": 149.5151577789974,
"count": 18201,
"self": 33.371286741000006,
"children": {
"TorchPolicy.sample_actions": {
"total": 116.1438710379974,
"count": 18201,
"self": 116.1438710379974
}
}
}
}
},
"workers": {
"total": 0.2630626730046117,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.9801396010005,
"count": 18201,
"is_parallel": true,
"self": 215.05956805100575,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006202620999999908,
"count": 1,
"is_parallel": true,
"self": 0.003383233999983304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028193870000166044,
"count": 10,
"is_parallel": true,
"self": 0.0028193870000166044
}
}
},
"UnityEnvironment.step": {
"total": 0.045030101000008926,
"count": 1,
"is_parallel": true,
"self": 0.00040144200002600883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030438599998205973,
"count": 1,
"is_parallel": true,
"self": 0.00030438599998205973
},
"communicator.exchange": {
"total": 0.04241994000000204,
"count": 1,
"is_parallel": true,
"self": 0.04241994000000204
},
"steps_from_proto": {
"total": 0.0019043329999988146,
"count": 1,
"is_parallel": true,
"self": 0.00045803500000829445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014462979999905201,
"count": 10,
"is_parallel": true,
"self": 0.0014462979999905201
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.92057154999472,
"count": 18200,
"is_parallel": true,
"self": 8.547274913987309,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.058109276002284,
"count": 18200,
"is_parallel": true,
"self": 5.058109276002284
},
"communicator.exchange": {
"total": 179.39987084600676,
"count": 18200,
"is_parallel": true,
"self": 179.39987084600676
},
"steps_from_proto": {
"total": 30.915316513998363,
"count": 18200,
"is_parallel": true,
"self": 6.555258097993772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.36005841600459,
"count": 182000,
"is_parallel": true,
"self": 24.36005841600459
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.167199995208648e-05,
"count": 1,
"self": 4.167199995208648e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 426.1123014980401,
"count": 343354,
"is_parallel": true,
"self": 9.665221117038413,
"children": {
"process_trajectory": {
"total": 243.53513270700157,
"count": 343354,
"is_parallel": true,
"self": 242.40782225700164,
"children": {
"RLTrainer._checkpoint": {
"total": 1.127310449999925,
"count": 4,
"is_parallel": true,
"self": 1.127310449999925
}
}
},
"_update_policy": {
"total": 172.9119476740001,
"count": 90,
"is_parallel": true,
"self": 45.19238854600036,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.71955912799973,
"count": 4587,
"is_parallel": true,
"self": 127.71955912799973
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.120924629000001,
"count": 1,
"self": 0.0008189069999389176,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12010572200006209,
"count": 1,
"self": 0.12010572200006209
}
}
}
}
}
}
}