|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.38276857137680054, |
|
"min": 0.38276857137680054, |
|
"max": 0.9076622724533081, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11513.6787109375, |
|
"min": 11513.6787109375, |
|
"max": 27084.642578125, |
|
"count": 18 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 328.9462365591398, |
|
"min": 307.65346534653463, |
|
"max": 661.7714285714286, |
|
"count": 18 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30592.0, |
|
"min": 23162.0, |
|
"max": 31986.0, |
|
"count": 18 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989980.0, |
|
"min": 479948.0, |
|
"max": 989980.0, |
|
"count": 18 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989980.0, |
|
"min": 479948.0, |
|
"max": 989980.0, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5688871741294861, |
|
"min": 0.19036932289600372, |
|
"max": 0.6378481388092041, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 158.7195281982422, |
|
"min": 45.498268127441406, |
|
"max": 183.0624237060547, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.010917271487414837, |
|
"min": 0.0013752927770838141, |
|
"max": 0.020950572565197945, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 3.0459187030792236, |
|
"min": 0.37270432710647583, |
|
"max": 5.0071868896484375, |
|
"count": 18 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5850064387565017, |
|
"min": 0.7093942442110607, |
|
"max": 1.6563727097077803, |
|
"count": 18 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 147.40559880435467, |
|
"min": 24.828798547387123, |
|
"max": 168.73519856482744, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5850064387565017, |
|
"min": 0.7093942442110607, |
|
"max": 1.6563727097077803, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 147.40559880435467, |
|
"min": 24.828798547387123, |
|
"max": 168.73519856482744, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.025173577382848897, |
|
"min": 0.024091804953344512, |
|
"max": 0.07632753398335938, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.3411426966049476, |
|
"min": 2.2467838548182044, |
|
"max": 3.648624841182027, |
|
"count": 18 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.10012599303061968, |
|
"min": 0.09594643640865788, |
|
"max": 0.10187956071337596, |
|
"count": 18 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.4017639024286757, |
|
"min": 1.3115939295414243, |
|
"max": 1.457446116563789, |
|
"count": 18 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01652623527628556, |
|
"min": 0.006338446456402316, |
|
"max": 0.016558457867073235, |
|
"count": 18 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23136729386799787, |
|
"min": 0.08239980393323011, |
|
"max": 0.23771413115239493, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.698568862414288e-06, |
|
"min": 7.698568862414288e-06, |
|
"max": 0.00016011586201267693, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010777996407380003, |
|
"min": 0.00010777996407380003, |
|
"max": 0.0021208518930496, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10256615714285715, |
|
"min": 0.10256615714285715, |
|
"max": 0.1533719384615385, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4359262000000002, |
|
"min": 1.4359262000000002, |
|
"max": 2.1069504000000006, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002663590985714286, |
|
"min": 0.0002663590985714286, |
|
"max": 0.005341856652307692, |
|
"count": 18 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003729027380000001, |
|
"min": 0.003729027380000001, |
|
"max": 0.07076434495999999, |
|
"count": 18 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007317533250898123, |
|
"min": 0.007317533250898123, |
|
"max": 0.011180681176483631, |
|
"count": 18 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10244546830654144, |
|
"min": 0.10244546830654144, |
|
"max": 0.1565295308828354, |
|
"count": 18 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 18 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 18 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1684824628", |
|
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
|
"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 --resume", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1684826850" |
|
}, |
|
"total": 2222.606720023001, |
|
"count": 1, |
|
"self": 1.0223579880021134, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.050478999999540974, |
|
"count": 1, |
|
"self": 0.050478999999540974 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2221.5338830349992, |
|
"count": 1, |
|
"self": 1.3507835598884412, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.2159504930004914, |
|
"count": 1, |
|
"self": 1.2159504930004914 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2218.839336225108, |
|
"count": 35419, |
|
"self": 1.3665946983819595, |
|
"children": { |
|
"env_step": { |
|
"total": 1405.1763573209246, |
|
"count": 35419, |
|
"self": 1325.2899403391784, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 79.06765266785078, |
|
"count": 35419, |
|
"self": 4.089022599871896, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 74.97863006797888, |
|
"count": 34364, |
|
"self": 74.97863006797888 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8187643138953717, |
|
"count": 35419, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2216.9513639020606, |
|
"count": 35419, |
|
"is_parallel": true, |
|
"self": 990.1446850330722, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.003068807000090601, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008292900001833914, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0022395169999072095, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0022395169999072095 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.10108899199985899, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007241379989864072, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005199970000830945, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005199970000830945 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.09761546100162377, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.09761546100162377 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0022293959991657175, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004743329973280197, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017550630018376978, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017550630018376978 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1226.8066788689885, |
|
"count": 35418, |
|
"is_parallel": true, |
|
"self": 25.720797587266134, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 14.728371341909224, |
|
"count": 35418, |
|
"is_parallel": true, |
|
"self": 14.728371341909224 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1107.6997279000316, |
|
"count": 35418, |
|
"is_parallel": true, |
|
"self": 1107.6997279000316 |
|
}, |
|
"steps_from_proto": { |
|
"total": 78.65778203978152, |
|
"count": 35418, |
|
"is_parallel": true, |
|
"self": 17.12307103698913, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 61.53471100279239, |
|
"count": 283344, |
|
"is_parallel": true, |
|
"self": 61.53471100279239 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 812.2963842058016, |
|
"count": 35419, |
|
"self": 2.71891580076408, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 84.88835608103909, |
|
"count": 35419, |
|
"self": 84.5583484630406, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3300076179984899, |
|
"count": 2, |
|
"self": 0.3300076179984899 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 724.6891123239984, |
|
"count": 258, |
|
"self": 261.35179579299984, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 463.3373165309986, |
|
"count": 25278, |
|
"self": 463.3373165309986 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0760013537947088e-06, |
|
"count": 1, |
|
"self": 1.0760013537947088e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1278116810008214, |
|
"count": 1, |
|
"self": 0.0024163260004570475, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12539535500036436, |
|
"count": 1, |
|
"self": 0.12539535500036436 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |