egksrikanth's picture
First Push
f4a445f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9892070889472961,
"min": 0.9892070889472961,
"max": 2.870063543319702,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9466.7119140625,
"min": 9466.7119140625,
"max": 29455.4609375,
"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": 13.03520393371582,
"min": 0.31968629360198975,
"max": 13.03520393371582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2541.86474609375,
"min": 62.01913833618164,
"max": 2635.422607421875,
"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": 0.07748381532192249,
"min": 0.061577864260157086,
"max": 0.07748381532192249,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30993526128768994,
"min": 0.2537554407089392,
"max": 0.3496101956138862,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22778849840602453,
"min": 0.11073098402337957,
"max": 0.28408296720362175,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9111539936240981,
"min": 0.44292393609351827,
"max": 1.358851961061066,
"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.CumulativeReward.mean": {
"value": 25.113636363636363,
"min": 3.1818181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 140.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.1818181818181817,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 140.0,
"max": 1400.0,
"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": "1728088093",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget0 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728088709"
},
"total": 616.515576367,
"count": 1,
"self": 0.5414106400000946,
"children": {
"run_training.setup": {
"total": 0.069172028999958,
"count": 1,
"self": 0.069172028999958
},
"TrainerController.start_learning": {
"total": 615.904993698,
"count": 1,
"self": 0.8953368499958287,
"children": {
"TrainerController._reset_env": {
"total": 3.1287780760000032,
"count": 1,
"self": 3.1287780760000032
},
"TrainerController.advance": {
"total": 611.7911947290042,
"count": 18204,
"self": 0.46560328999692047,
"children": {
"env_step": {
"total": 611.3255914390073,
"count": 18204,
"self": 468.29833916200784,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.593071612995,
"count": 18204,
"self": 2.616763799992441,
"children": {
"TorchPolicy.evaluate": {
"total": 139.97630781300256,
"count": 18204,
"self": 139.97630781300256
}
}
},
"workers": {
"total": 0.4341806640044865,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 614.0368061909958,
"count": 18204,
"is_parallel": true,
"self": 293.71280248399523,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0038930270000037126,
"count": 1,
"is_parallel": true,
"self": 0.0008666099998890786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003026417000114634,
"count": 10,
"is_parallel": true,
"self": 0.003026417000114634
}
}
},
"UnityEnvironment.step": {
"total": 0.047516639000036776,
"count": 1,
"is_parallel": true,
"self": 0.0009035630000653327,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005830640000112908,
"count": 1,
"is_parallel": true,
"self": 0.0005830640000112908
},
"communicator.exchange": {
"total": 0.04338663599997972,
"count": 1,
"is_parallel": true,
"self": 0.04338663599997972
},
"steps_from_proto": {
"total": 0.002643375999980435,
"count": 1,
"is_parallel": true,
"self": 0.0005005010000331822,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002142874999947253,
"count": 10,
"is_parallel": true,
"self": 0.002142874999947253
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 320.32400370700054,
"count": 18203,
"is_parallel": true,
"self": 15.062487361007356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.555819185999496,
"count": 18203,
"is_parallel": true,
"self": 7.555819185999496
},
"communicator.exchange": {
"total": 253.4709262669794,
"count": 18203,
"is_parallel": true,
"self": 253.4709262669794
},
"steps_from_proto": {
"total": 44.234770893014286,
"count": 18203,
"is_parallel": true,
"self": 8.806954636026433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.42781625698785,
"count": 182030,
"is_parallel": true,
"self": 35.42781625698785
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014275599994562072,
"count": 1,
"self": 0.00014275599994562072,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 604.9290381669481,
"count": 741907,
"is_parallel": true,
"self": 17.78955232995679,
"children": {
"process_trajectory": {
"total": 328.48607915199153,
"count": 741907,
"is_parallel": true,
"self": 327.5890363359916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8970428159999528,
"count": 4,
"is_parallel": true,
"self": 0.8970428159999528
}
}
},
"_update_policy": {
"total": 258.6534066849998,
"count": 90,
"is_parallel": true,
"self": 72.30179672399584,
"children": {
"TorchPPOOptimizer.update": {
"total": 186.351609961004,
"count": 4587,
"is_parallel": true,
"self": 186.351609961004
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08954128699997455,
"count": 1,
"self": 0.0012686279999343242,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08827265900004022,
"count": 1,
"self": 0.08827265900004022
}
}
}
}
}
}
}