jegeblad's picture
First Push
61e9a8f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8040768504142761,
"min": 0.8040768504142761,
"max": 2.8379011154174805,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7641.9462890625,
"min": 7641.9462890625,
"max": 28969.294921875,
"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": 13.122721672058105,
"min": 0.378519207239151,
"max": 13.122721672058105,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2558.9306640625,
"min": 73.43272399902344,
"max": 2676.98291015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0715483362924608,
"min": 0.0664638717446317,
"max": 0.07507761804265423,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2861933451698432,
"min": 0.2658554869785268,
"max": 0.36565636913839944,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19029670802547652,
"min": 0.11848030422595056,
"max": 0.2966272187934202,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7611868321019061,
"min": 0.47392121690380223,
"max": 1.483136093967101,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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.Environment.CumulativeReward.mean": {
"value": 25.681818181818183,
"min": 3.590909090909091,
"max": 26.327272727272728,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 158.0,
"max": 1448.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.590909090909091,
"max": 26.327272727272728,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 158.0,
"max": 1448.0,
"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": "1748086827",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --force --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748087314"
},
"total": 486.9300944910001,
"count": 1,
"self": 0.48854942100024346,
"children": {
"run_training.setup": {
"total": 0.021704849999878206,
"count": 1,
"self": 0.021704849999878206
},
"TrainerController.start_learning": {
"total": 486.41984021999997,
"count": 1,
"self": 0.30643627695690157,
"children": {
"TrainerController._reset_env": {
"total": 2.1777290669997456,
"count": 1,
"self": 2.1777290669997456
},
"TrainerController.advance": {
"total": 483.84443277304354,
"count": 18192,
"self": 0.35155690001784023,
"children": {
"env_step": {
"total": 295.0802644350297,
"count": 18192,
"self": 225.02334460497877,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.85831993000829,
"count": 18192,
"self": 1.2086983419872013,
"children": {
"TorchPolicy.evaluate": {
"total": 68.64962158802109,
"count": 18192,
"self": 68.64962158802109
}
}
},
"workers": {
"total": 0.19859990004260908,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 485.06091074699725,
"count": 18192,
"is_parallel": true,
"self": 287.16733117898684,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002225781000106508,
"count": 1,
"is_parallel": true,
"self": 0.0006653410000581061,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001560440000048402,
"count": 10,
"is_parallel": true,
"self": 0.001560440000048402
}
}
},
"UnityEnvironment.step": {
"total": 0.03654692999998588,
"count": 1,
"is_parallel": true,
"self": 0.000578642000164109,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003826590000244323,
"count": 1,
"is_parallel": true,
"self": 0.0003826590000244323
},
"communicator.exchange": {
"total": 0.033636789999945904,
"count": 1,
"is_parallel": true,
"self": 0.033636789999945904
},
"steps_from_proto": {
"total": 0.0019488389998514322,
"count": 1,
"is_parallel": true,
"self": 0.0004130720003558963,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015357669994955359,
"count": 10,
"is_parallel": true,
"self": 0.0015357669994955359
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.8935795680104,
"count": 18191,
"is_parallel": true,
"self": 9.693212871039123,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.448032051022437,
"count": 18191,
"is_parallel": true,
"self": 5.448032051022437
},
"communicator.exchange": {
"total": 151.74449205395422,
"count": 18191,
"is_parallel": true,
"self": 151.74449205395422
},
"steps_from_proto": {
"total": 31.00784259199463,
"count": 18191,
"is_parallel": true,
"self": 5.459735341037685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.548107250956946,
"count": 181910,
"is_parallel": true,
"self": 25.548107250956946
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 188.41261143799602,
"count": 18192,
"self": 0.38613604597730955,
"children": {
"process_trajectory": {
"total": 27.032632964016557,
"count": 18192,
"self": 26.57824021201668,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45439275199987605,
"count": 4,
"self": 0.45439275199987605
}
}
},
"_update_policy": {
"total": 160.99384242800215,
"count": 90,
"self": 64.82036724101363,
"children": {
"TorchPPOOptimizer.update": {
"total": 96.17347518698853,
"count": 7645,
"self": 96.17347518698853
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2000000424450263e-06,
"count": 1,
"self": 1.2000000424450263e-06
},
"TrainerController._save_models": {
"total": 0.09124090299974341,
"count": 1,
"self": 0.0010554379996392527,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09018546500010416,
"count": 1,
"self": 0.09018546500010416
}
}
}
}
}
}
}