bhushan02's picture
First Push
fbb0888 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7182103991508484,
"min": 0.7182103991508484,
"max": 2.846219778060913,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6825.87158203125,
"min": 6825.87158203125,
"max": 29054.2109375,
"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": 13.176970481872559,
"min": 0.30675479769706726,
"max": 13.176970481872559,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2569.50927734375,
"min": 59.51042938232422,
"max": 2667.15966796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06944685627012422,
"min": 0.06144597981154791,
"max": 0.07708604275502891,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27778742508049686,
"min": 0.2660779890141509,
"max": 0.36559963022819814,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19494209789177952,
"min": 0.12556787742548348,
"max": 0.2869202275486553,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7797683915671181,
"min": 0.5022715097019339,
"max": 1.3858505388100943,
"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": 25.954545454545453,
"min": 3.3636363636363638,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 148.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 3.3636363636363638,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 148.0,
"max": 1428.0,
"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": "1745423077",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745423517"
},
"total": 440.326725602,
"count": 1,
"self": 0.43924346700009664,
"children": {
"run_training.setup": {
"total": 0.03239464199998565,
"count": 1,
"self": 0.03239464199998565
},
"TrainerController.start_learning": {
"total": 439.8550874929999,
"count": 1,
"self": 0.39816709800095396,
"children": {
"TrainerController._reset_env": {
"total": 3.1188282020000315,
"count": 1,
"self": 3.1188282020000315
},
"TrainerController.advance": {
"total": 436.2514422839987,
"count": 18192,
"self": 0.4034268800079417,
"children": {
"env_step": {
"total": 311.4127357489955,
"count": 18192,
"self": 237.8424081489951,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.33606769700009,
"count": 18192,
"self": 1.323328990009486,
"children": {
"TorchPolicy.evaluate": {
"total": 72.0127387069906,
"count": 18192,
"self": 72.0127387069906
}
}
},
"workers": {
"total": 0.23425990300029298,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.23437789701507,
"count": 18192,
"is_parallel": true,
"self": 230.2807225290219,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005152004000024135,
"count": 1,
"is_parallel": true,
"self": 0.0035687250002638393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015832789997602958,
"count": 10,
"is_parallel": true,
"self": 0.0015832789997602958
}
}
},
"UnityEnvironment.step": {
"total": 0.036277810999990834,
"count": 1,
"is_parallel": true,
"self": 0.0006099290000065594,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004260800000110976,
"count": 1,
"is_parallel": true,
"self": 0.0004260800000110976
},
"communicator.exchange": {
"total": 0.03337817199997062,
"count": 1,
"is_parallel": true,
"self": 0.03337817199997062
},
"steps_from_proto": {
"total": 0.0018636300000025585,
"count": 1,
"is_parallel": true,
"self": 0.0003707980004037381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014928319995988204,
"count": 10,
"is_parallel": true,
"self": 0.0014928319995988204
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.95365536799318,
"count": 18191,
"is_parallel": true,
"self": 9.861973325010467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.629625527999224,
"count": 18191,
"is_parallel": true,
"self": 5.629625527999224
},
"communicator.exchange": {
"total": 159.78230027499478,
"count": 18191,
"is_parallel": true,
"self": 159.78230027499478
},
"steps_from_proto": {
"total": 32.679756239988706,
"count": 18191,
"is_parallel": true,
"self": 5.951473804979628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.728282435009078,
"count": 181910,
"is_parallel": true,
"self": 26.728282435009078
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.43527965499527,
"count": 18192,
"self": 0.5006313139843996,
"children": {
"process_trajectory": {
"total": 28.227728588010677,
"count": 18192,
"self": 27.71559327401087,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5121353139998064,
"count": 4,
"self": 0.5121353139998064
}
}
},
"_update_policy": {
"total": 95.7069197530002,
"count": 90,
"self": 39.05337526899609,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.6535444840041,
"count": 4587,
"self": 56.6535444840041
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2310001693549566e-06,
"count": 1,
"self": 1.2310001693549566e-06
},
"TrainerController._save_models": {
"total": 0.08664867800007414,
"count": 1,
"self": 0.0008656550000978314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08578302299997631,
"count": 1,
"self": 0.08578302299997631
}
}
}
}
}
}
}