niks-salodkar's picture
first training
168132f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9679405689239502,
"min": 0.9679405689239502,
"max": 2.846729278564453,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9263.19140625,
"min": 9263.19140625,
"max": 29215.982421875,
"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": 13.456722259521484,
"min": 0.33531254529953003,
"max": 13.456722259521484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2624.060791015625,
"min": 65.0506362915039,
"max": 2732.2646484375,
"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": 0.0752620911365489,
"min": 0.06327364768002038,
"max": 0.0762578739620307,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3010483645461956,
"min": 0.2566328512718125,
"max": 0.3812893698101535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1775248686180395,
"min": 0.12768007157480016,
"max": 0.2996939753200494,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.710099474472158,
"min": 0.5107202862992006,
"max": 1.4984698766002469,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082009730600007e-05,
"min": 8.082009730600007e-05,
"max": 0.0029188200027059994,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00032328038922400026,
"min": 0.00032328038922400026,
"max": 0.013851600038280001,
"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": 26.522727272727273,
"min": 3.2045454545454546,
"max": 26.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1167.0,
"min": 141.0,
"max": 1442.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.522727272727273,
"min": 3.2045454545454546,
"max": 26.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1167.0,
"min": 141.0,
"max": 1442.0,
"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": "1679064850",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679065335"
},
"total": 485.052132799,
"count": 1,
"self": 0.8532897449997563,
"children": {
"run_training.setup": {
"total": 0.10585591500012015,
"count": 1,
"self": 0.10585591500012015
},
"TrainerController.start_learning": {
"total": 484.0929871390001,
"count": 1,
"self": 0.5925209950178214,
"children": {
"TrainerController._reset_env": {
"total": 9.658645269999852,
"count": 1,
"self": 9.658645269999852
},
"TrainerController.advance": {
"total": 473.6185324749829,
"count": 18211,
"self": 0.28929721699250877,
"children": {
"env_step": {
"total": 473.3292352579904,
"count": 18211,
"self": 340.41724144598084,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.62502553402283,
"count": 18211,
"self": 2.4070635140146805,
"children": {
"TorchPolicy.evaluate": {
"total": 130.21796202000814,
"count": 18211,
"self": 130.21796202000814
}
}
},
"workers": {
"total": 0.2869682779867162,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.38523172299006,
"count": 18211,
"is_parallel": true,
"self": 231.84705854798926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006452782999986084,
"count": 1,
"is_parallel": true,
"self": 0.00404743499984761,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002405348000138474,
"count": 10,
"is_parallel": true,
"self": 0.002405348000138474
}
}
},
"UnityEnvironment.step": {
"total": 0.050565001999984815,
"count": 1,
"is_parallel": true,
"self": 0.0004127490001337719,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003561640000953048,
"count": 1,
"is_parallel": true,
"self": 0.0003561640000953048
},
"communicator.exchange": {
"total": 0.04779554999981883,
"count": 1,
"is_parallel": true,
"self": 0.04779554999981883
},
"steps_from_proto": {
"total": 0.002000538999936907,
"count": 1,
"is_parallel": true,
"self": 0.000490999999556152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015095390003807552,
"count": 10,
"is_parallel": true,
"self": 0.0015095390003807552
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.5381731750008,
"count": 18210,
"is_parallel": true,
"self": 9.833080900936238,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.549395417026744,
"count": 18210,
"is_parallel": true,
"self": 5.549395417026744
},
"communicator.exchange": {
"total": 201.83758430703165,
"count": 18210,
"is_parallel": true,
"self": 201.83758430703165
},
"steps_from_proto": {
"total": 33.31811255000616,
"count": 18210,
"is_parallel": true,
"self": 6.7189650860370875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.599147463969075,
"count": 182100,
"is_parallel": true,
"self": 26.599147463969075
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014164499998514657,
"count": 1,
"self": 0.00014164499998514657,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.91811499394294,
"count": 426408,
"is_parallel": true,
"self": 10.896090392794349,
"children": {
"process_trajectory": {
"total": 262.58056300215003,
"count": 426408,
"is_parallel": true,
"self": 261.5911919571504,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9893710449996433,
"count": 4,
"is_parallel": true,
"self": 0.9893710449996433
}
}
},
"_update_policy": {
"total": 196.44146159899856,
"count": 90,
"is_parallel": true,
"self": 72.14369200500414,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.29776959399442,
"count": 4587,
"is_parallel": true,
"self": 124.29776959399442
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22314675399957196,
"count": 1,
"self": 0.0028624809997381817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22028427299983377,
"count": 1,
"self": 0.22028427299983377
}
}
}
}
}
}
}