eoulster's picture
First training of SnowballTarget
04773fe
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8988369703292847,
"min": 0.8978126049041748,
"max": 2.8687262535095215,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8591.982421875,
"min": 8591.982421875,
"max": 29504.849609375,
"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": 13.089356422424316,
"min": 0.39677146077156067,
"max": 13.089356422424316,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.424560546875,
"min": 76.97366333007812,
"max": 2664.71728515625,
"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": 0.06148041205654176,
"min": 0.06148041205654176,
"max": 0.07735341942064705,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24592164822616705,
"min": 0.24592164822616705,
"max": 0.3841867617105462,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19910274599404895,
"min": 0.10972341076087425,
"max": 0.2929453248486799,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7964109839761958,
"min": 0.438893643043497,
"max": 1.4647266242433996,
"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": 25.613636363636363,
"min": 3.2954545454545454,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 145.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.2954545454545454,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 145.0,
"max": 1413.0,
"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": "1678220691",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "1.20.0",
"end_time_seconds": "1678221331"
},
"total": 640.5529346980002,
"count": 1,
"self": 0.551035058999787,
"children": {
"run_training.setup": {
"total": 0.15710810200016567,
"count": 1,
"self": 0.15710810200016567
},
"TrainerController.start_learning": {
"total": 639.8447915370002,
"count": 1,
"self": 0.9930020190367941,
"children": {
"TrainerController._reset_env": {
"total": 10.82172968299983,
"count": 1,
"self": 10.82172968299983
},
"TrainerController.advance": {
"total": 627.8936442889635,
"count": 18203,
"self": 0.479343464966405,
"children": {
"env_step": {
"total": 627.4143008239971,
"count": 18203,
"self": 494.36408169698507,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.61569777199202,
"count": 18203,
"self": 2.616592810973998,
"children": {
"TorchPolicy.evaluate": {
"total": 129.99910496101802,
"count": 18203,
"self": 21.819597098990926,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.1795078620271,
"count": 18203,
"self": 108.1795078620271
}
}
}
}
},
"workers": {
"total": 0.4345213550200242,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 637.4771180650041,
"count": 18203,
"is_parallel": true,
"self": 288.52629614601483,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002920165999967139,
"count": 1,
"is_parallel": true,
"self": 0.0009918020004988648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019283639994682744,
"count": 10,
"is_parallel": true,
"self": 0.0019283639994682744
}
}
},
"UnityEnvironment.step": {
"total": 0.1282724180000514,
"count": 1,
"is_parallel": true,
"self": 0.0007546960000581748,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047343500000351924,
"count": 1,
"is_parallel": true,
"self": 0.00047343500000351924
},
"communicator.exchange": {
"total": 0.12468149599999379,
"count": 1,
"is_parallel": true,
"self": 0.12468149599999379
},
"steps_from_proto": {
"total": 0.002362790999995923,
"count": 1,
"is_parallel": true,
"self": 0.0005322540000634035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018305369999325194,
"count": 10,
"is_parallel": true,
"self": 0.0018305369999325194
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 348.9508219189893,
"count": 18202,
"is_parallel": true,
"self": 14.866517107010623,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.669054501982373,
"count": 18202,
"is_parallel": true,
"self": 7.669054501982373
},
"communicator.exchange": {
"total": 279.64233527798024,
"count": 18202,
"is_parallel": true,
"self": 279.64233527798024
},
"steps_from_proto": {
"total": 46.772915032016044,
"count": 18202,
"is_parallel": true,
"self": 10.873193123095007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.89972190892104,
"count": 182020,
"is_parallel": true,
"self": 35.89972190892104
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002448619998176582,
"count": 1,
"self": 0.0002448619998176582,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 622.3595410690609,
"count": 610655,
"is_parallel": true,
"self": 16.44871484715941,
"children": {
"process_trajectory": {
"total": 342.38771695689957,
"count": 610655,
"is_parallel": true,
"self": 341.0409489158992,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3467680410003595,
"count": 4,
"is_parallel": true,
"self": 1.3467680410003595
}
}
},
"_update_policy": {
"total": 263.52310926500195,
"count": 90,
"is_parallel": true,
"self": 85.24963538301563,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.27347388198632,
"count": 4587,
"is_parallel": true,
"self": 178.27347388198632
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13617068400026255,
"count": 1,
"self": 0.0011106160000053933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13506006800025716,
"count": 1,
"self": 0.13506006800025716
}
}
}
}
}
}
}