WilsonLai's picture
First Push
be56ccf verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4090090990066528,
"min": 1.4090090990066528,
"max": 2.843280076980591,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 14507.158203125,
"min": 13491.2431640625,
"max": 29024.203125,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 9.358089447021484,
"min": 0.4480263590812683,
"max": 9.358089447021484,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1909.0501708984375,
"min": 86.9171142578125,
"max": 1909.0501708984375,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.063641879955471,
"min": 0.06326430462735623,
"max": 0.0716604814697348,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.318209399777355,
"min": 0.2530572185094249,
"max": 0.34296177723830196,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21881272325328754,
"min": 0.11773453035743395,
"max": 0.2742251067184934,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0940636162664377,
"min": 0.4709381214297358,
"max": 1.3711255335924672,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 19.381818181818183,
"min": 3.3636363636363638,
"max": 19.381818181818183,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1066.0,
"min": 148.0,
"max": 1066.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.381818181818183,
"min": 3.3636363636363638,
"max": 19.381818181818183,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1066.0,
"min": 148.0,
"max": 1066.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1757495911",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757496188"
},
"total": 276.66096150600004,
"count": 1,
"self": 0.5441158059999225,
"children": {
"run_training.setup": {
"total": 0.04426830600004905,
"count": 1,
"self": 0.04426830600004905
},
"TrainerController.start_learning": {
"total": 276.07257739400006,
"count": 1,
"self": 0.3039082409985099,
"children": {
"TrainerController._reset_env": {
"total": 3.634664084999997,
"count": 1,
"self": 3.634664084999997
},
"TrainerController.advance": {
"total": 272.06007519600155,
"count": 9128,
"self": 0.30761155099548887,
"children": {
"env_step": {
"total": 191.1646956680044,
"count": 9128,
"self": 163.31734276900312,
"children": {
"SubprocessEnvManager._take_step": {
"total": 27.657436976001406,
"count": 9128,
"self": 0.9512509770029851,
"children": {
"TorchPolicy.evaluate": {
"total": 26.70618599899842,
"count": 9128,
"self": 26.70618599899842
}
}
},
"workers": {
"total": 0.18991592299988724,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 274.94423724500365,
"count": 9128,
"is_parallel": true,
"self": 133.49073976500404,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006535057999997207,
"count": 1,
"is_parallel": true,
"self": 0.004365288000030887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00216976999996632,
"count": 10,
"is_parallel": true,
"self": 0.00216976999996632
}
}
},
"UnityEnvironment.step": {
"total": 0.041714339000009204,
"count": 1,
"is_parallel": true,
"self": 0.0006979520000527373,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000438120999945113,
"count": 1,
"is_parallel": true,
"self": 0.000438120999945113
},
"communicator.exchange": {
"total": 0.0384296110000264,
"count": 1,
"is_parallel": true,
"self": 0.0384296110000264
},
"steps_from_proto": {
"total": 0.002148654999984956,
"count": 1,
"is_parallel": true,
"self": 0.0004661670000700724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016824879999148834,
"count": 10,
"is_parallel": true,
"self": 0.0016824879999148834
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 141.4534974799996,
"count": 9127,
"is_parallel": true,
"self": 6.53863654500077,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.660453877999828,
"count": 9127,
"is_parallel": true,
"self": 3.660453877999828
},
"communicator.exchange": {
"total": 111.1735423640007,
"count": 9127,
"is_parallel": true,
"self": 111.1735423640007
},
"steps_from_proto": {
"total": 20.08086469299832,
"count": 9127,
"is_parallel": true,
"self": 3.858073052019165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 16.222791640979153,
"count": 91270,
"is_parallel": true,
"self": 16.222791640979153
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 80.58776797700165,
"count": 9128,
"self": 0.3864675779963136,
"children": {
"process_trajectory": {
"total": 15.101305857005627,
"count": 9128,
"self": 14.72731322300558,
"children": {
"RLTrainer._checkpoint": {
"total": 0.37399263400004656,
"count": 2,
"self": 0.37399263400004656
}
}
},
"_update_policy": {
"total": 65.0999945419997,
"count": 45,
"self": 24.401230743999065,
"children": {
"TorchPPOOptimizer.update": {
"total": 40.69876379800064,
"count": 2292,
"self": 40.69876379800064
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0360000715081696e-06,
"count": 1,
"self": 1.0360000715081696e-06
},
"TrainerController._save_models": {
"total": 0.07392883599993638,
"count": 1,
"self": 0.001125158999911946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07280367700002444,
"count": 1,
"self": 0.07280367700002444
}
}
}
}
}
}
}