gmshuler95's picture
first training of SnowballTarget
ae85ebf
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.3857568502426147,
"min": 1.3857568502426147,
"max": 2.8812692165374756,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13200.7197265625,
"min": 13200.7197265625,
"max": 29602.16015625,
"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": 11.6624174118042,
"min": 0.3226674199104309,
"max": 11.6624174118042,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2274.17138671875,
"min": 62.59748077392578,
"max": 2316.61962890625,
"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": 0.04953769437634037,
"min": 0.040557000892855896,
"max": 0.061445652310188364,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.19815077750536148,
"min": 0.16222800357142358,
"max": 0.26048074811842525,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3816614410219093,
"min": 0.12747787730768323,
"max": 0.4051946632564068,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.5266457640876372,
"min": 0.5099115092307329,
"max": 2.025973316282034,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.735097306000006e-06,
"min": 6.735097306000006e-06,
"max": 0.000243235002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.6940389224000025e-05,
"min": 2.6940389224000025e-05,
"max": 0.0011543000382800003,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101347,
"min": 0.101347,
"max": 0.148647,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.405388,
"min": 0.405388,
"max": 0.73086,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00027913060000000025,
"min": 0.00027913060000000025,
"max": 0.0097296706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001116522400000001,
"min": 0.001116522400000001,
"max": 0.046175828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.954545454545453,
"min": 2.3636363636363638,
"max": 22.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1010.0,
"min": 104.0,
"max": 1258.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.954545454545453,
"min": 2.3636363636363638,
"max": 22.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1010.0,
"min": 104.0,
"max": 1258.0,
"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": "1693058329",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/gavin/mambaforge/envs/HuggingFace-Unit5/bin/mlagents-learn /home/gavin/Documents/HuggingFace/Unit5/ml-agents/content/ml-agents/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1693058777"
},
"total": 447.22853547200066,
"count": 1,
"self": 0.3228218750009546,
"children": {
"run_training.setup": {
"total": 0.01128943599997001,
"count": 1,
"self": 0.01128943599997001
},
"TrainerController.start_learning": {
"total": 446.89442416099973,
"count": 1,
"self": 0.5126851310105849,
"children": {
"TrainerController._reset_env": {
"total": 0.6011814399998912,
"count": 1,
"self": 0.6011814399998912
},
"TrainerController.advance": {
"total": 445.6626719649894,
"count": 18200,
"self": 0.228819077915432,
"children": {
"env_step": {
"total": 445.43385288707395,
"count": 18200,
"self": 341.5335951120651,
"children": {
"SubprocessEnvManager._take_step": {
"total": 103.64196179803457,
"count": 18200,
"self": 1.495194020980307,
"children": {
"TorchPolicy.evaluate": {
"total": 102.14676777705427,
"count": 18200,
"self": 102.14676777705427
}
}
},
"workers": {
"total": 0.2582959769742956,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 445.6430271840072,
"count": 18200,
"is_parallel": true,
"self": 187.7744489389197,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001792300000488467,
"count": 1,
"is_parallel": true,
"self": 0.000496380001095531,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001295919999392936,
"count": 10,
"is_parallel": true,
"self": 0.001295919999392936
}
}
},
"UnityEnvironment.step": {
"total": 0.03168528900005185,
"count": 1,
"is_parallel": true,
"self": 0.0003594489999159123,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003024319994437974,
"count": 1,
"is_parallel": true,
"self": 0.0003024319994437974
},
"communicator.exchange": {
"total": 0.029932163000012224,
"count": 1,
"is_parallel": true,
"self": 0.029932163000012224
},
"steps_from_proto": {
"total": 0.001091245000679919,
"count": 1,
"is_parallel": true,
"self": 0.00021883500176045345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008724099989194656,
"count": 10,
"is_parallel": true,
"self": 0.0008724099989194656
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 257.8685782450875,
"count": 18199,
"is_parallel": true,
"self": 7.673712870034251,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.838100775069506,
"count": 18199,
"is_parallel": true,
"self": 4.838100775069506
},
"communicator.exchange": {
"total": 223.87420313198254,
"count": 18199,
"is_parallel": true,
"self": 223.87420313198254
},
"steps_from_proto": {
"total": 21.482561468001222,
"count": 18199,
"is_parallel": true,
"self": 4.229607299924282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.25295416807694,
"count": 181990,
"is_parallel": true,
"self": 17.25295416807694
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024107599983835826,
"count": 1,
"self": 0.00024107599983835826,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.38596000698726,
"count": 325666,
"is_parallel": true,
"self": 6.787127136058189,
"children": {
"process_trajectory": {
"total": 258.0810822529229,
"count": 325666,
"is_parallel": true,
"self": 257.298526629922,
"children": {
"RLTrainer._checkpoint": {
"total": 0.782555623000917,
"count": 4,
"is_parallel": true,
"self": 0.782555623000917
}
}
},
"_update_policy": {
"total": 178.51775061800618,
"count": 90,
"is_parallel": true,
"self": 44.55162457201277,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.9661260459934,
"count": 2160,
"is_parallel": true,
"self": 133.9661260459934
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1176445490000333,
"count": 1,
"self": 0.0008863659995768103,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11675818300045648,
"count": 1,
"self": 0.11675818300045648
}
}
}
}
}
}
}