rishipatel92's picture
First Push of SnowBallTarget
f7090d1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.852695643901825,
"min": 0.852695643901825,
"max": 2.8739514350891113,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8732.4560546875,
"min": 8210.48046875,
"max": 29432.13671875,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.6020686626434326,
"min": 0.09584341198205948,
"max": 2.662080764770508,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 504.80133056640625,
"min": 18.5936222076416,
"max": 543.064453125,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.15909090909091,
"min": 3.272727272727273,
"max": 25.962962962962962,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 144.0,
"max": 1426.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.272727272727273,
"max": 25.962962962962962,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 144.0,
"max": 1426.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06620381637163897,
"min": 0.062281041308773905,
"max": 0.07334943803876844,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2648152654865559,
"min": 0.1868431239263217,
"max": 0.29339775215507374,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.10793324217828523,
"min": 0.05565207241799194,
"max": 0.1371442951952411,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.43173296871314093,
"min": 0.1669562172539758,
"max": 0.5160827368291706,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.141697952799997e-06,
"min": 6.141697952799997e-06,
"max": 0.0002930304023231999,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.456679181119999e-05,
"min": 2.456679181119999e-05,
"max": 0.0010805664398112,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1020472,
"min": 0.1020472,
"max": 0.1976768,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4081888,
"min": 0.31847040000000004,
"max": 0.7601887999999999,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00011215527999999996,
"min": 0.00011215527999999996,
"max": 0.00488407232,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00044862111999999986,
"min": 0.00044862111999999986,
"max": 0.01801342112,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673375009",
"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": "1673375545"
},
"total": 536.535963872,
"count": 1,
"self": 0.4411005590000059,
"children": {
"run_training.setup": {
"total": 0.11608919299999343,
"count": 1,
"self": 0.11608919299999343
},
"TrainerController.start_learning": {
"total": 535.97877412,
"count": 1,
"self": 0.6656289899959802,
"children": {
"TrainerController._reset_env": {
"total": 7.888809207000008,
"count": 1,
"self": 7.888809207000008
},
"TrainerController.advance": {
"total": 527.305964063004,
"count": 22800,
"self": 0.31904194702008226,
"children": {
"env_step": {
"total": 526.9869221159839,
"count": 22800,
"self": 348.658101822983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 177.99100360700686,
"count": 22800,
"self": 1.6732547340046722,
"children": {
"TorchPolicy.evaluate": {
"total": 176.3177488730022,
"count": 22800,
"self": 38.74815777599076,
"children": {
"TorchPolicy.sample_actions": {
"total": 137.56959109701143,
"count": 22800,
"self": 137.56959109701143
}
}
}
}
},
"workers": {
"total": 0.33781668599408476,
"count": 22800,
"self": 0.0,
"children": {
"worker_root": {
"total": 534.3307781739984,
"count": 22800,
"is_parallel": true,
"self": 258.8708320339923,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006014525000068716,
"count": 1,
"is_parallel": true,
"self": 0.0029910270001209938,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003023497999947722,
"count": 10,
"is_parallel": true,
"self": 0.003023497999947722
}
}
},
"UnityEnvironment.step": {
"total": 0.034150907000025654,
"count": 1,
"is_parallel": true,
"self": 0.0005946790000734836,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034124299997984053,
"count": 1,
"is_parallel": true,
"self": 0.00034124299997984053
},
"communicator.exchange": {
"total": 0.03131415300003937,
"count": 1,
"is_parallel": true,
"self": 0.03131415300003937
},
"steps_from_proto": {
"total": 0.0019008319999329615,
"count": 1,
"is_parallel": true,
"self": 0.0004259449999608478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014748869999721137,
"count": 10,
"is_parallel": true,
"self": 0.0014748869999721137
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 275.4599461400061,
"count": 22799,
"is_parallel": true,
"self": 10.565694285013137,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.2496687620212015,
"count": 22799,
"is_parallel": true,
"self": 6.2496687620212015
},
"communicator.exchange": {
"total": 220.33470419496962,
"count": 22799,
"is_parallel": true,
"self": 220.33470419496962
},
"steps_from_proto": {
"total": 38.309878898002125,
"count": 22799,
"is_parallel": true,
"self": 8.132889554971484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.17698934303064,
"count": 227990,
"is_parallel": true,
"self": 30.17698934303064
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.452300004231802e-05,
"count": 1,
"self": 4.452300004231802e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 523.5355852310325,
"count": 433986,
"is_parallel": true,
"self": 11.586212020041671,
"children": {
"process_trajectory": {
"total": 302.53978229099266,
"count": 433986,
"is_parallel": true,
"self": 301.68361412999263,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8561681610000278,
"count": 5,
"is_parallel": true,
"self": 0.8561681610000278
}
}
},
"_update_policy": {
"total": 209.4095909199982,
"count": 85,
"is_parallel": true,
"self": 59.45969367499265,
"children": {
"TorchPPOOptimizer.update": {
"total": 149.94989724500556,
"count": 5694,
"is_parallel": true,
"self": 149.94989724500556
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11832733699998244,
"count": 1,
"self": 0.0008926250000058644,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11743471199997657,
"count": 1,
"self": 0.11743471199997657
}
}
}
}
}
}
}