|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1671365648508072, |
|
"min": 0.1671365648508072, |
|
"max": 1.435519814491272, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5051.53564453125, |
|
"min": 5051.53564453125, |
|
"max": 43547.9296875, |
|
"count": 66 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1979974.0, |
|
"min": 29952.0, |
|
"max": 1979974.0, |
|
"count": 66 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1979974.0, |
|
"min": 29952.0, |
|
"max": 1979974.0, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5358601808547974, |
|
"min": -0.11700937896966934, |
|
"max": 0.7015327215194702, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 153.25601196289062, |
|
"min": -27.73122215270996, |
|
"max": 205.54908752441406, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.016772892326116562, |
|
"min": -0.028345569968223572, |
|
"max": 0.5080322623252869, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.797047138214111, |
|
"min": -7.596612930297852, |
|
"max": 120.40364837646484, |
|
"count": 66 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06841565237846227, |
|
"min": 0.06532535654130496, |
|
"max": 0.07275287406912842, |
|
"count": 66 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9578191332984717, |
|
"min": 0.5005644435790935, |
|
"max": 1.06032787480702, |
|
"count": 66 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014863313009430255, |
|
"min": 0.00020938235665503006, |
|
"max": 0.017486680912914367, |
|
"count": 66 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20808638213202357, |
|
"min": 0.002721970636515391, |
|
"max": 0.24481353278080115, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 5.299373233575e-06, |
|
"min": 5.299373233575e-06, |
|
"max": 0.0002975753150939428, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 7.419122527005e-05, |
|
"min": 7.419122527005e-05, |
|
"max": 0.003853526515491201, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.101766425, |
|
"min": 0.101766425, |
|
"max": 0.19919177142857142, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.42472995, |
|
"min": 1.3845568000000001, |
|
"max": 2.6845087999999997, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00018646585750000001, |
|
"min": 0.00018646585750000001, |
|
"max": 0.009919257965714285, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.002610522005, |
|
"min": 0.002610522005, |
|
"max": 0.12846242912, |
|
"count": 66 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.00727482233196497, |
|
"min": 0.00727482233196497, |
|
"max": 0.5102919936180115, |
|
"count": 66 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10184751451015472, |
|
"min": 0.10184751451015472, |
|
"max": 3.5720438957214355, |
|
"count": 66 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 301.45, |
|
"min": 262.8695652173913, |
|
"max": 999.0, |
|
"count": 66 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30145.0, |
|
"min": 15984.0, |
|
"max": 32926.0, |
|
"count": 66 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4984939842671157, |
|
"min": -1.0000000521540642, |
|
"max": 1.632751289917075, |
|
"count": 66 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 149.84939842671156, |
|
"min": -32.000001668930054, |
|
"max": 187.76639834046364, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4984939842671157, |
|
"min": -1.0000000521540642, |
|
"max": 1.632751289917075, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 149.84939842671156, |
|
"min": -32.000001668930054, |
|
"max": 187.76639834046364, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.023019604940782302, |
|
"min": 0.02293750223749236, |
|
"max": 10.073955454863608, |
|
"count": 66 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.30196049407823, |
|
"min": 2.280451965620159, |
|
"max": 161.18328727781773, |
|
"count": 66 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 66 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 66 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1673546413", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --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": "1673550519" |
|
}, |
|
"total": 4105.909641729999, |
|
"count": 1, |
|
"self": 0.4249261779996232, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10533701100030157, |
|
"count": 1, |
|
"self": 0.10533701100030157 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 4105.379378540999, |
|
"count": 1, |
|
"self": 2.335072648023015, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.182917680000173, |
|
"count": 1, |
|
"self": 6.182917680000173 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 4096.777086414975, |
|
"count": 128504, |
|
"self": 2.3665180063662774, |
|
"children": { |
|
"env_step": { |
|
"total": 2804.564204866173, |
|
"count": 128504, |
|
"self": 2606.02531857308, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 197.0560491029837, |
|
"count": 128504, |
|
"self": 8.256623862006563, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 188.79942524097714, |
|
"count": 125053, |
|
"self": 64.08367310995618, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 124.71575213102096, |
|
"count": 125053, |
|
"self": 124.71575213102096 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.4828371901094215, |
|
"count": 128504, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 4096.73127901483, |
|
"count": 128504, |
|
"is_parallel": true, |
|
"self": 1683.692985817922, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0016672239999024896, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000595927001995733, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010712969979067566, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010712969979067566 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.055998612000621506, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005208380016483716, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00038594799934799084, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00038594799934799084 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05338423299963324, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05338423299963324 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017075929999919026, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004413309989104164, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012662620010814862, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012662620010814862 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2413.038293196908, |
|
"count": 128503, |
|
"is_parallel": true, |
|
"self": 54.75101230896598, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 44.80629490994579, |
|
"count": 128503, |
|
"is_parallel": true, |
|
"self": 44.80629490994579 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2110.9525191950434, |
|
"count": 128503, |
|
"is_parallel": true, |
|
"self": 2110.9525191950434 |
|
}, |
|
"steps_from_proto": { |
|
"total": 202.52846678295282, |
|
"count": 128503, |
|
"is_parallel": true, |
|
"self": 44.341408289201354, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 158.18705849375146, |
|
"count": 1028024, |
|
"is_parallel": true, |
|
"self": 158.18705849375146 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1289.846363542436, |
|
"count": 128504, |
|
"self": 4.523266965513358, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 287.9918757849491, |
|
"count": 128504, |
|
"self": 287.6241151779486, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3677606070004913, |
|
"count": 4, |
|
"self": 0.3677606070004913 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 997.3312207919735, |
|
"count": 916, |
|
"self": 386.153883986045, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 611.1773368059285, |
|
"count": 45597, |
|
"self": 611.1773368059285 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.759998308960348e-07, |
|
"count": 1, |
|
"self": 8.759998308960348e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08430092200069339, |
|
"count": 1, |
|
"self": 0.0013292070016177604, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08297171499907563, |
|
"count": 1, |
|
"self": 0.08297171499907563 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |