|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6654035449028015, |
|
"min": 0.6198781132698059, |
|
"max": 1.4324965476989746, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 19738.53125, |
|
"min": 18725.27734375, |
|
"max": 43456.21484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989993.0, |
|
"min": 29952.0, |
|
"max": 989993.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989993.0, |
|
"min": 29952.0, |
|
"max": 989993.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.11871465295553207, |
|
"min": -0.1126789078116417, |
|
"max": 0.12750495970249176, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 29.67866325378418, |
|
"min": -27.155616760253906, |
|
"max": 31.23871421813965, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.032399341464042664, |
|
"min": 0.003081351052969694, |
|
"max": 0.7086651921272278, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 8.099835395812988, |
|
"min": 0.7549310326576233, |
|
"max": 167.95364379882812, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06821755483854629, |
|
"min": 0.06369347492094293, |
|
"max": 0.07224014179821414, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.955045767739648, |
|
"min": 0.49766075681565847, |
|
"max": 1.0625874550748324, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.009722731603168151, |
|
"min": 0.00033316030966757965, |
|
"max": 0.029824517492252407, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.1361182424443541, |
|
"min": 0.004664244335346115, |
|
"max": 0.20877162244576686, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.309211849342858e-06, |
|
"min": 7.309211849342858e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010232896589080001, |
|
"min": 0.00010232896589080001, |
|
"max": 0.0033826619724460997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10243637142857143, |
|
"min": 0.10243637142857143, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4341092, |
|
"min": 1.3691136000000002, |
|
"max": 2.5275539000000005, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002533935057142858, |
|
"min": 0.0002533935057142858, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003547509080000001, |
|
"min": 0.003547509080000001, |
|
"max": 0.11278263461, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.014446069486439228, |
|
"min": 0.014446069486439228, |
|
"max": 0.6883009076118469, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.20224496722221375, |
|
"min": 0.20224496722221375, |
|
"max": 4.818106174468994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 711.047619047619, |
|
"min": 706.05, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29864.0, |
|
"min": 15984.0, |
|
"max": 32329.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.6022139226281366, |
|
"min": -1.0000000521540642, |
|
"max": 0.6022139226281366, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 25.895198673009872, |
|
"min": -32.000001668930054, |
|
"max": 25.895198673009872, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.6022139226281366, |
|
"min": -1.0000000521540642, |
|
"max": 0.6022139226281366, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 25.895198673009872, |
|
"min": -32.000001668930054, |
|
"max": 25.895198673009872, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.1066799313452658, |
|
"min": 0.1066799313452658, |
|
"max": 15.622168138623238, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.587237047846429, |
|
"min": 4.424240807886235, |
|
"max": 249.9546902179718, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1710473530", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.2.1+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1710475723" |
|
}, |
|
"total": 2192.71295035, |
|
"count": 1, |
|
"self": 0.594711155999903, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.05610658500000909, |
|
"count": 1, |
|
"self": 0.05610658500000909 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2192.062132609, |
|
"count": 1, |
|
"self": 1.4695135829570063, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.0383218329999977, |
|
"count": 1, |
|
"self": 3.0383218329999977 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2187.467418628043, |
|
"count": 63226, |
|
"self": 1.5136654030375212, |
|
"children": { |
|
"env_step": { |
|
"total": 1538.7644160830012, |
|
"count": 63226, |
|
"self": 1396.2548176159912, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 141.55793911503753, |
|
"count": 63226, |
|
"self": 5.134145834031472, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 136.42379328100606, |
|
"count": 62537, |
|
"self": 136.42379328100606 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9516593519724097, |
|
"count": 63226, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2186.8228899619703, |
|
"count": 63226, |
|
"is_parallel": true, |
|
"self": 923.4372933499669, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.009720857999980126, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004632070000070598, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.005088787999909528, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.005088787999909528 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05563899100002345, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008412480000856704, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00047900399999889487, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00047900399999889487 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05241736199997149, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05241736199997149 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0019013769999673968, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003871120000553674, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015142649999120295, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015142649999120295 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1263.3855966120034, |
|
"count": 63225, |
|
"is_parallel": true, |
|
"self": 37.25135674900298, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 26.753710269017347, |
|
"count": 63225, |
|
"is_parallel": true, |
|
"self": 26.753710269017347 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1088.415419579995, |
|
"count": 63225, |
|
"is_parallel": true, |
|
"self": 1088.415419579995 |
|
}, |
|
"steps_from_proto": { |
|
"total": 110.96511001398818, |
|
"count": 63225, |
|
"is_parallel": true, |
|
"self": 22.883532576998164, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 88.08157743699002, |
|
"count": 505800, |
|
"is_parallel": true, |
|
"self": 88.08157743699002 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 647.1893371420044, |
|
"count": 63226, |
|
"self": 2.780257229003837, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 135.16311682500015, |
|
"count": 63226, |
|
"self": 134.88140251200008, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2817143130000659, |
|
"count": 2, |
|
"self": 0.2817143130000659 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 509.24596308800045, |
|
"count": 440, |
|
"self": 299.65798846402004, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 209.58797462398041, |
|
"count": 22794, |
|
"self": 209.58797462398041 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0230000953015406e-06, |
|
"count": 1, |
|
"self": 1.0230000953015406e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08687754199991105, |
|
"count": 1, |
|
"self": 0.0013713739999730024, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08550616799993804, |
|
"count": 1, |
|
"self": 0.08550616799993804 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |