|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4841180741786957, |
|
"min": 0.4770418703556061, |
|
"max": 1.3938826322555542, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14717.189453125, |
|
"min": 14112.806640625, |
|
"max": 42284.82421875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989987.0, |
|
"min": 29890.0, |
|
"max": 989987.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989987.0, |
|
"min": 29890.0, |
|
"max": 989987.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5993238687515259, |
|
"min": -0.32549071311950684, |
|
"max": 0.6077452301979065, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 167.21136474609375, |
|
"min": -77.14129638671875, |
|
"max": 171.3841552734375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.003141416935250163, |
|
"min": -0.30730104446411133, |
|
"max": 0.7080830931663513, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -0.8764553070068359, |
|
"min": -78.0544662475586, |
|
"max": 167.81568908691406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06511705456555707, |
|
"min": 0.06511705456555707, |
|
"max": 0.07418011290014717, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9767558184833559, |
|
"min": 0.5934409032011774, |
|
"max": 1.0611411751015112, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0152793147885758, |
|
"min": 0.0006066122193355063, |
|
"max": 0.029338310884001358, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.229189721828637, |
|
"min": 0.00667273441269057, |
|
"max": 0.44007466326002037, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.4769575077133354e-06, |
|
"min": 7.4769575077133354e-06, |
|
"max": 0.0002947608392463875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011215436261570004, |
|
"min": 0.00011215436261570004, |
|
"max": 0.003507596330801299, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249228666666667, |
|
"min": 0.10249228666666667, |
|
"max": 0.1982536125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5373843, |
|
"min": 1.4779296000000002, |
|
"max": 2.5691987000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002589794380000001, |
|
"min": 0.0002589794380000001, |
|
"max": 0.00982553588875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003884691570000001, |
|
"min": 0.003884691570000001, |
|
"max": 0.11694295013, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.017012285068631172, |
|
"min": 0.016789482906460762, |
|
"max": 0.6819204092025757, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.25518426299095154, |
|
"min": 0.23505276441574097, |
|
"max": 5.4553632736206055, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 314.0430107526882, |
|
"min": 314.0430107526882, |
|
"max": 992.1875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29206.0, |
|
"min": 17584.0, |
|
"max": 33322.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6455195550199435, |
|
"min": -0.9303563004359603, |
|
"max": 1.6580505115421196, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 151.3877990618348, |
|
"min": -29.77140161395073, |
|
"max": 157.51479859650135, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6455195550199435, |
|
"min": -0.9303563004359603, |
|
"max": 1.6580505115421196, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 151.3877990618348, |
|
"min": -29.77140161395073, |
|
"max": 157.51479859650135, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.054804565043646704, |
|
"min": 0.054804565043646704, |
|
"max": 14.2016558084223, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.0420199840154964, |
|
"min": 5.0420199840154964, |
|
"max": 255.6298045516014, |
|
"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": "1677941123", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.22.4", |
|
"end_time_seconds": "1677943415" |
|
}, |
|
"total": 2292.505173122, |
|
"count": 1, |
|
"self": 0.5200078720004058, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11890567099999316, |
|
"count": 1, |
|
"self": 0.11890567099999316 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2291.8662595789997, |
|
"count": 1, |
|
"self": 1.4429241569696387, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.563649079000015, |
|
"count": 1, |
|
"self": 10.563649079000015 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2279.7654722620305, |
|
"count": 63741, |
|
"self": 1.5401958020070197, |
|
"children": { |
|
"env_step": { |
|
"total": 1521.5567800880267, |
|
"count": 63741, |
|
"self": 1402.6595376420132, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 118.02103697099506, |
|
"count": 63741, |
|
"self": 4.9781059339505305, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 113.04293103704453, |
|
"count": 62562, |
|
"self": 38.39692370605741, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 74.64600733098712, |
|
"count": 62562, |
|
"self": 74.64600733098712 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8762054750185371, |
|
"count": 63741, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2286.7530822410267, |
|
"count": 63741, |
|
"is_parallel": true, |
|
"self": 1005.4881854780306, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007792905000030714, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0052833589999750075, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002509546000055707, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002509546000055707 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0726149669999927, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005961959999467581, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004638550000208852, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004638550000208852 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06969753800001399, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06969753800001399 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018573780000110673, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000504099999943719, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013532780000673483, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013532780000673483 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1281.2648967629962, |
|
"count": 63740, |
|
"is_parallel": true, |
|
"self": 32.09705234994772, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.780313530040303, |
|
"count": 63740, |
|
"is_parallel": true, |
|
"self": 24.780313530040303 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1127.1192436039983, |
|
"count": 63740, |
|
"is_parallel": true, |
|
"self": 1127.1192436039983 |
|
}, |
|
"steps_from_proto": { |
|
"total": 97.26828727901, |
|
"count": 63740, |
|
"is_parallel": true, |
|
"self": 23.4695597550799, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 73.7987275239301, |
|
"count": 509920, |
|
"is_parallel": true, |
|
"self": 73.7987275239301 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 756.6684963719969, |
|
"count": 63741, |
|
"self": 2.6297460490510502, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 169.43247389394645, |
|
"count": 63741, |
|
"self": 169.23914006794638, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19333382600007099, |
|
"count": 2, |
|
"self": 0.19333382600007099 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 584.6062764289993, |
|
"count": 454, |
|
"self": 226.58819682899542, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 358.0180796000039, |
|
"count": 22788, |
|
"self": 358.0180796000039 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.590000106778461e-07, |
|
"count": 1, |
|
"self": 8.590000106778461e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09421322199978022, |
|
"count": 1, |
|
"self": 0.001479267999457079, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09273395400032314, |
|
"count": 1, |
|
"self": 0.09273395400032314 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |