nossal's picture
First push, minimal training
5679476
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.7255338430404663,
"min": 1.7255338430404663,
"max": 2.864640712738037,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 17728.134765625,
"min": 17118.19140625,
"max": 29336.78515625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 7.8852219581604,
"min": 0.3039523661136627,
"max": 7.8852219581604,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1608.5853271484375,
"min": 58.966758728027344,
"max": 1608.5853271484375,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06833732816237756,
"min": 0.06222269721811423,
"max": 0.07504014130767353,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34168664081188777,
"min": 0.24889078887245691,
"max": 0.3752007065383676,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23116904380274755,
"min": 0.11355999895649979,
"max": 0.2744280527181485,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.1558452190137378,
"min": 0.45423999582599917,
"max": 1.3128022183390227,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 16.854545454545455,
"min": 3.3636363636363638,
"max": 16.854545454545455,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 927.0,
"min": 148.0,
"max": 927.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 16.854545454545455,
"min": 3.3636363636363638,
"max": 16.854545454545455,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 927.0,
"min": 148.0,
"max": 927.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677788938",
"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": "1.22.4",
"end_time_seconds": "1677789197"
},
"total": 259.06107947500004,
"count": 1,
"self": 0.7924288599999727,
"children": {
"run_training.setup": {
"total": 0.18315430300003754,
"count": 1,
"self": 0.18315430300003754
},
"TrainerController.start_learning": {
"total": 258.08549631200003,
"count": 1,
"self": 0.3856486240066488,
"children": {
"TrainerController._reset_env": {
"total": 9.609496005999972,
"count": 1,
"self": 9.609496005999972
},
"TrainerController.advance": {
"total": 247.89026274699336,
"count": 9145,
"self": 0.16442402099511355,
"children": {
"env_step": {
"total": 247.72583872599824,
"count": 9145,
"self": 173.4453867490011,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.1163152230011,
"count": 9145,
"self": 0.8207567959960329,
"children": {
"TorchPolicy.evaluate": {
"total": 73.29555842700506,
"count": 9145,
"self": 16.15781357599809,
"children": {
"TorchPolicy.sample_actions": {
"total": 57.13774485100697,
"count": 9145,
"self": 57.13774485100697
}
}
}
}
},
"workers": {
"total": 0.164136753996047,
"count": 9145,
"self": 0.0,
"children": {
"worker_root": {
"total": 257.10512863999236,
"count": 9145,
"is_parallel": true,
"self": 125.04941174699258,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008742424999979903,
"count": 1,
"is_parallel": true,
"self": 0.006638771999860182,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021036530001197207,
"count": 10,
"is_parallel": true,
"self": 0.0021036530001197207
}
}
},
"UnityEnvironment.step": {
"total": 0.04802606900000228,
"count": 1,
"is_parallel": true,
"self": 0.0005931719999239249,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003248760000360562,
"count": 1,
"is_parallel": true,
"self": 0.0003248760000360562
},
"communicator.exchange": {
"total": 0.04522586000001638,
"count": 1,
"is_parallel": true,
"self": 0.04522586000001638
},
"steps_from_proto": {
"total": 0.001882161000025917,
"count": 1,
"is_parallel": true,
"self": 0.00042215100006615103,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001460009999959766,
"count": 10,
"is_parallel": true,
"self": 0.001460009999959766
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 132.05571689299978,
"count": 9144,
"is_parallel": true,
"self": 5.380242350013873,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.842962104997241,
"count": 9144,
"is_parallel": true,
"self": 2.842962104997241
},
"communicator.exchange": {
"total": 106.85560603399108,
"count": 9144,
"is_parallel": true,
"self": 106.85560603399108
},
"steps_from_proto": {
"total": 16.97690640399759,
"count": 9144,
"is_parallel": true,
"self": 3.9250747629874922,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.051831641010097,
"count": 91440,
"is_parallel": true,
"self": 13.051831641010097
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0004193860000896166,
"count": 1,
"self": 0.0004193860000896166,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 246.0702306519969,
"count": 226863,
"is_parallel": true,
"self": 5.662165619003815,
"children": {
"process_trajectory": {
"total": 141.84268658799334,
"count": 226863,
"is_parallel": true,
"self": 140.70175700199343,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1409295859999133,
"count": 4,
"is_parallel": true,
"self": 1.1409295859999133
}
}
},
"_update_policy": {
"total": 98.56537844499974,
"count": 45,
"is_parallel": true,
"self": 34.943106471999954,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.62227197299978,
"count": 2292,
"is_parallel": true,
"self": 63.62227197299978
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1996695489999638,
"count": 1,
"self": 0.0012116619999460454,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19845788700001776,
"count": 1,
"self": 0.19845788700001776
}
}
}
}
}
}
}