codewithpurav's picture
First Push
526e878 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8445367813110352,
"min": 0.8445367813110352,
"max": 2.8669636249542236,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8026.4775390625,
"min": 8026.4775390625,
"max": 29265.96484375,
"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": 12.691551208496094,
"min": 0.4032234847545624,
"max": 12.691551208496094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2474.8525390625,
"min": 78.22535705566406,
"max": 2570.47314453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0680713547732083,
"min": 0.06109064766924883,
"max": 0.07581895417563062,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2722854190928332,
"min": 0.2443625906769953,
"max": 0.3660951276485553,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20404651037910404,
"min": 0.12218782407866206,
"max": 0.2892432813258732,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8161860415164162,
"min": 0.48875129631464825,
"max": 1.375285131674187,
"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": 25.045454545454547,
"min": 3.7045454545454546,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 163.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.7045454545454546,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 163.0,
"max": 1368.0,
"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": "1750486560",
"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 --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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750486970"
},
"total": 410.582856195,
"count": 1,
"self": 0.4418769289998181,
"children": {
"run_training.setup": {
"total": 0.02413465100016765,
"count": 1,
"self": 0.02413465100016765
},
"TrainerController.start_learning": {
"total": 410.116844615,
"count": 1,
"self": 0.31804418996830464,
"children": {
"TrainerController._reset_env": {
"total": 3.304766144000041,
"count": 1,
"self": 3.304766144000041
},
"TrainerController.advance": {
"total": 406.3997760330317,
"count": 18192,
"self": 0.3457215550563433,
"children": {
"env_step": {
"total": 289.75468127899876,
"count": 18192,
"self": 222.3450674790281,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.20920598399925,
"count": 18192,
"self": 1.1732137239955591,
"children": {
"TorchPolicy.evaluate": {
"total": 66.0359922600037,
"count": 18192,
"self": 66.0359922600037
}
}
},
"workers": {
"total": 0.20040781597140267,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 408.7658815730085,
"count": 18192,
"is_parallel": true,
"self": 213.11999068401428,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005898996000041734,
"count": 1,
"is_parallel": true,
"self": 0.004481027999190701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014179680008510331,
"count": 10,
"is_parallel": true,
"self": 0.0014179680008510331
}
}
},
"UnityEnvironment.step": {
"total": 0.034842817000026116,
"count": 1,
"is_parallel": true,
"self": 0.0005661869997766189,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004299189999983355,
"count": 1,
"is_parallel": true,
"self": 0.0004299189999983355
},
"communicator.exchange": {
"total": 0.031898243000114235,
"count": 1,
"is_parallel": true,
"self": 0.031898243000114235
},
"steps_from_proto": {
"total": 0.001948468000136927,
"count": 1,
"is_parallel": true,
"self": 0.0003504240000893333,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015980440000475937,
"count": 10,
"is_parallel": true,
"self": 0.0015980440000475937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.64589088899424,
"count": 18191,
"is_parallel": true,
"self": 9.427165114964964,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.12079207600641,
"count": 18191,
"is_parallel": true,
"self": 5.12079207600641
},
"communicator.exchange": {
"total": 151.20508073200813,
"count": 18191,
"is_parallel": true,
"self": 151.20508073200813
},
"steps_from_proto": {
"total": 29.892852966014743,
"count": 18191,
"is_parallel": true,
"self": 5.326924521000592,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.56592844501415,
"count": 181910,
"is_parallel": true,
"self": 24.56592844501415
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.29937319897658,
"count": 18192,
"self": 0.3880521679818685,
"children": {
"process_trajectory": {
"total": 25.278645509995158,
"count": 18192,
"self": 24.887477343995215,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3911681659999431,
"count": 4,
"self": 0.3911681659999431
}
}
},
"_update_policy": {
"total": 90.63267552099956,
"count": 90,
"self": 36.952057581997224,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.68061793900233,
"count": 4587,
"self": 53.68061793900233
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.059999683813658e-07,
"count": 1,
"self": 9.059999683813658e-07
},
"TrainerController._save_models": {
"total": 0.0942573419999917,
"count": 1,
"self": 0.0009103370000502764,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09334700499994142,
"count": 1,
"self": 0.09334700499994142
}
}
}
}
}
}
}