BogdanTurbal's picture
First Push
aec286f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8678367733955383,
"min": 0.861872673034668,
"max": 2.8763105869293213,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8247.9208984375,
"min": 8247.9208984375,
"max": 29361.37890625,
"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": 13.237685203552246,
"min": 0.3575952351093292,
"max": 13.237685203552246,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2581.3486328125,
"min": 69.37347412109375,
"max": 2703.87451171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06722229981189194,
"min": 0.062171241143540314,
"max": 0.07272181908035646,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26888919924756777,
"min": 0.2600750495384644,
"max": 0.3636090954017823,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18977277729587227,
"min": 0.10136019179994679,
"max": 0.3254906561444787,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7590911091834891,
"min": 0.40544076719978717,
"max": 1.3889245458093344,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"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.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": 25.977272727272727,
"min": 2.977272727272727,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1143.0,
"min": 131.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.977272727272727,
"min": 2.977272727272727,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1143.0,
"min": 131.0,
"max": 1433.0,
"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": "1738683739",
"python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738684119"
},
"total": 380.172486046,
"count": 1,
"self": 0.321196390999944,
"children": {
"run_training.setup": {
"total": 0.022058865000076366,
"count": 1,
"self": 0.022058865000076366
},
"TrainerController.start_learning": {
"total": 379.82923079,
"count": 1,
"self": 0.3558614500109343,
"children": {
"TrainerController._reset_env": {
"total": 2.024557480999988,
"count": 1,
"self": 2.024557480999988
},
"TrainerController.advance": {
"total": 377.3596870909889,
"count": 18192,
"self": 0.32599077797419795,
"children": {
"env_step": {
"total": 262.72067079800695,
"count": 18192,
"self": 196.265953464017,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.2530548899889,
"count": 18192,
"self": 1.1623858599861023,
"children": {
"TorchPolicy.evaluate": {
"total": 65.0906690300028,
"count": 18192,
"self": 65.0906690300028
}
}
},
"workers": {
"total": 0.2016624440010446,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 379.05369137600064,
"count": 18192,
"is_parallel": true,
"self": 206.02483343100164,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023067140000421205,
"count": 1,
"is_parallel": true,
"self": 0.000700577000316116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016061369997260044,
"count": 10,
"is_parallel": true,
"self": 0.0016061369997260044
}
}
},
"UnityEnvironment.step": {
"total": 0.026887367999961498,
"count": 1,
"is_parallel": true,
"self": 0.00037212200004432816,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000259678000020358,
"count": 1,
"is_parallel": true,
"self": 0.000259678000020358
},
"communicator.exchange": {
"total": 0.02504236699996909,
"count": 1,
"is_parallel": true,
"self": 0.02504236699996909
},
"steps_from_proto": {
"total": 0.0012132009999277216,
"count": 1,
"is_parallel": true,
"self": 0.00027567900008307333,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009375219998446482,
"count": 10,
"is_parallel": true,
"self": 0.0009375219998446482
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 173.028857944999,
"count": 18191,
"is_parallel": true,
"self": 6.115731944013305,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.2352464639973277,
"count": 18191,
"is_parallel": true,
"self": 3.2352464639973277
},
"communicator.exchange": {
"total": 143.88778045399795,
"count": 18191,
"is_parallel": true,
"self": 143.88778045399795
},
"steps_from_proto": {
"total": 19.790099082990423,
"count": 18191,
"is_parallel": true,
"self": 3.8840979129541893,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.906001170036234,
"count": 181910,
"is_parallel": true,
"self": 15.906001170036234
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 114.31302551500778,
"count": 18192,
"self": 0.39984979301311796,
"children": {
"process_trajectory": {
"total": 24.489706779994776,
"count": 18192,
"self": 24.094132046994787,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39557473299998946,
"count": 4,
"self": 0.39557473299998946
}
}
},
"_update_policy": {
"total": 89.42346894199989,
"count": 90,
"self": 35.417006856998796,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.00646208500109,
"count": 4587,
"self": 54.00646208500109
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0150000662179082e-06,
"count": 1,
"self": 1.0150000662179082e-06
},
"TrainerController._save_models": {
"total": 0.0891237530000808,
"count": 1,
"self": 0.0009190170001147635,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08820473599996603,
"count": 1,
"self": 0.08820473599996603
}
}
}
}
}
}
}