|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3079421818256378, |
|
"min": 0.3079421818256378, |
|
"max": 1.4653654098510742, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9208.703125, |
|
"min": 9208.703125, |
|
"max": 44453.32421875, |
|
"count": 37 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1109886.0, |
|
"min": 29904.0, |
|
"max": 1109886.0, |
|
"count": 37 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1109886.0, |
|
"min": 29904.0, |
|
"max": 1109886.0, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7282056212425232, |
|
"min": -0.14689964056015015, |
|
"max": 0.7282056212425232, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 208.99501037597656, |
|
"min": -34.815216064453125, |
|
"max": 208.99501037597656, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.005693688057363033, |
|
"min": -0.010266827419400215, |
|
"max": 0.2772565186023712, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.6340885162353516, |
|
"min": -2.813110828399658, |
|
"max": 65.70979309082031, |
|
"count": 37 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06502705050626813, |
|
"min": 0.06502705050626813, |
|
"max": 0.07391043653402757, |
|
"count": 37 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9103787070877538, |
|
"min": 0.5674283807558784, |
|
"max": 1.1086565480104136, |
|
"count": 37 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.013246345796644509, |
|
"min": 0.0021518852914151, |
|
"max": 0.016139538479841405, |
|
"count": 37 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.18544884115302313, |
|
"min": 0.025822623496981202, |
|
"max": 0.22595353871777968, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 0.0001904964579297643, |
|
"min": 0.0001904964579297643, |
|
"max": 0.0002984034005322, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0026669504110167002, |
|
"min": 0.0023872272042576, |
|
"max": 0.0041172984275672335, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.16349880714285714, |
|
"min": 0.16349880714285714, |
|
"max": 0.1994678, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 2.2889833, |
|
"min": 1.5957424, |
|
"max": 2.872432766666667, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0063535308335714285, |
|
"min": 0.0063535308335714285, |
|
"max": 0.00994683322, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.08894943167, |
|
"min": 0.07957466576, |
|
"max": 0.13725603339, |
|
"count": 37 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010376361198723316, |
|
"min": 0.008851609192788601, |
|
"max": 0.3764885365962982, |
|
"count": 37 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14526905119419098, |
|
"min": 0.12392253428697586, |
|
"max": 3.0119082927703857, |
|
"count": 37 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 286.50961538461536, |
|
"min": 272.875, |
|
"max": 990.0588235294117, |
|
"count": 37 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29797.0, |
|
"min": 16831.0, |
|
"max": 32144.0, |
|
"count": 37 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6365480582731275, |
|
"min": -0.8733412207049482, |
|
"max": 1.7104761789242426, |
|
"count": 37 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 170.20099806040525, |
|
"min": -27.456601679325104, |
|
"max": 189.43639809638262, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6365480582731275, |
|
"min": -0.8733412207049482, |
|
"max": 1.7104761789242426, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 170.20099806040525, |
|
"min": -27.456601679325104, |
|
"max": 189.43639809638262, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.030860550049720378, |
|
"min": 0.028261452546238224, |
|
"max": 7.589311210548177, |
|
"count": 37 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.209497205170919, |
|
"min": 2.604007639703923, |
|
"max": 129.018290579319, |
|
"count": 37 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 37 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 37 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1660202942", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1.21.6", |
|
"end_time_seconds": "1660205219" |
|
}, |
|
"total": 2277.361686525, |
|
"count": 1, |
|
"self": 0.2899749149996751, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0420872849999796, |
|
"count": 1, |
|
"self": 0.0420872849999796 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2277.0296243250004, |
|
"count": 1, |
|
"self": 1.4522744300061277, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.568040686000018, |
|
"count": 1, |
|
"self": 10.568040686000018 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2264.8508460519943, |
|
"count": 71867, |
|
"self": 1.5563831289855443, |
|
"children": { |
|
"env_step": { |
|
"total": 1481.2367061579791, |
|
"count": 71867, |
|
"self": 1365.9924279429506, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 114.46112863100251, |
|
"count": 71867, |
|
"self": 5.038649549951799, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 109.42247908105071, |
|
"count": 69874, |
|
"self": 38.21339551906328, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 71.20908356198743, |
|
"count": 69874, |
|
"self": 71.20908356198743 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7831495840259208, |
|
"count": 71867, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2272.6336747399914, |
|
"count": 71867, |
|
"is_parallel": true, |
|
"self": 1017.0100531099179, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005756088999987696, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0045572900000365735, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011987989999511228, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011987989999511228 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0451832190000232, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005898320000596868, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000449232999983451, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000449232999983451 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04247218799997654, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04247218799997654 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001671966000003522, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000462084000048435, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001209881999955087, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001209881999955087 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1255.6236216300736, |
|
"count": 71866, |
|
"is_parallel": true, |
|
"self": 30.0061024970546, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 25.06209682701001, |
|
"count": 71866, |
|
"is_parallel": true, |
|
"self": 25.06209682701001 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1099.315978173021, |
|
"count": 71866, |
|
"is_parallel": true, |
|
"self": 1099.315978173021 |
|
}, |
|
"steps_from_proto": { |
|
"total": 101.23944413298807, |
|
"count": 71866, |
|
"is_parallel": true, |
|
"self": 24.808650029035277, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 76.43079410395279, |
|
"count": 574928, |
|
"is_parallel": true, |
|
"self": 76.43079410395279 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 782.0577567650298, |
|
"count": 71867, |
|
"self": 2.7755640250568376, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 179.90654594497306, |
|
"count": 71867, |
|
"self": 179.70380031997348, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20274562499957938, |
|
"count": 2, |
|
"self": 0.20274562499957938 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 599.375646795, |
|
"count": 517, |
|
"self": 232.01140013197562, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 367.36424666302435, |
|
"count": 25429, |
|
"self": 367.36424666302435 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.7219999790540896e-06, |
|
"count": 1, |
|
"self": 1.7219999790540896e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1584614349999356, |
|
"count": 1, |
|
"self": 0.0022537059999194753, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.15620772900001612, |
|
"count": 1, |
|
"self": 0.15620772900001612 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |