|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4396551847457886, |
|
"min": 0.4396551847457886, |
|
"max": 1.391548991203308, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13161.517578125, |
|
"min": 13161.517578125, |
|
"max": 42214.03125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989941.0, |
|
"min": 29952.0, |
|
"max": 989941.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989941.0, |
|
"min": 29952.0, |
|
"max": 989941.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.45281553268432617, |
|
"min": -0.1800701916217804, |
|
"max": 0.5031939744949341, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 122.7130126953125, |
|
"min": -42.6766357421875, |
|
"max": 135.86236572265625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.03403672203421593, |
|
"min": 0.0056115612387657166, |
|
"max": 0.5939701795578003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 9.22395133972168, |
|
"min": 1.520733118057251, |
|
"max": 140.77093505859375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06476632071861473, |
|
"min": 0.06440121945662507, |
|
"max": 0.07394794854310215, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9067284900606062, |
|
"min": 0.4774663622572017, |
|
"max": 1.074361404927913, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.018741669808155708, |
|
"min": 0.001202503200516351, |
|
"max": 0.018741669808155708, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.26238337731417993, |
|
"min": 0.008417522403614458, |
|
"max": 0.26238337731417993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.384083252957147e-06, |
|
"min": 7.384083252957147e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010337716554140006, |
|
"min": 0.00010337716554140006, |
|
"max": 0.0036324358891880997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10246132857142858, |
|
"min": 0.10246132857142858, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4344586000000001, |
|
"min": 1.3691136000000002, |
|
"max": 2.6108119000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025588672428571445, |
|
"min": 0.00025588672428571445, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003582414140000002, |
|
"min": 0.003582414140000002, |
|
"max": 0.12110010881, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.017936760559678078, |
|
"min": 0.017726516351103783, |
|
"max": 0.6130093336105347, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2511146366596222, |
|
"min": 0.2511146366596222, |
|
"max": 4.291065216064453, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 398.9736842105263, |
|
"min": 367.81481481481484, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30322.0, |
|
"min": 15984.0, |
|
"max": 31968.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4957262902079445, |
|
"min": -1.0000000521540642, |
|
"max": 1.5459999729480063, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 113.67519805580378, |
|
"min": -32.000001668930054, |
|
"max": 122.43579834699631, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4957262902079445, |
|
"min": -1.0000000521540642, |
|
"max": 1.5459999729480063, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 113.67519805580378, |
|
"min": -32.000001668930054, |
|
"max": 122.43579834699631, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.07370381586090509, |
|
"min": 0.07189388586848508, |
|
"max": 11.804267760366201, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.601490005428786, |
|
"min": 5.47153862711275, |
|
"max": 188.86828416585922, |
|
"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": "1673638307", |
|
"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 --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": "1673640440" |
|
}, |
|
"total": 2132.170624842, |
|
"count": 1, |
|
"self": 0.4933884150000267, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11826202100019145, |
|
"count": 1, |
|
"self": 0.11826202100019145 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2131.558974406, |
|
"count": 1, |
|
"self": 1.2410631389784612, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.247740610999927, |
|
"count": 1, |
|
"self": 10.247740610999927 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2119.973484765021, |
|
"count": 63711, |
|
"self": 1.3737178881015097, |
|
"children": { |
|
"env_step": { |
|
"total": 1407.5015681459718, |
|
"count": 63711, |
|
"self": 1300.3228378689641, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 106.39662315901523, |
|
"count": 63711, |
|
"self": 4.436344639983872, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 101.96027851903136, |
|
"count": 62581, |
|
"self": 34.55857385299555, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 67.40170466603581, |
|
"count": 62581, |
|
"self": 67.40170466603581 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.782107117992382, |
|
"count": 63711, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2126.9092807480138, |
|
"count": 63711, |
|
"is_parallel": true, |
|
"self": 929.5254545799667, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007137400999909005, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004405902000144124, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002731498999764881, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002731498999764881 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0501198409999688, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005406759999004862, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00046890499993423873, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046890499993423873 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04747559700012971, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04747559700012971 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001634663000004366, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004108010002710216, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012238619997333444, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012238619997333444 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1197.383826168047, |
|
"count": 63710, |
|
"is_parallel": true, |
|
"self": 30.362966142013192, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.214603850988624, |
|
"count": 63710, |
|
"is_parallel": true, |
|
"self": 24.214603850988624 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1043.8963723280099, |
|
"count": 63710, |
|
"is_parallel": true, |
|
"self": 1043.8963723280099 |
|
}, |
|
"steps_from_proto": { |
|
"total": 98.90988384703542, |
|
"count": 63710, |
|
"is_parallel": true, |
|
"self": 23.023201704008443, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 75.88668214302697, |
|
"count": 509680, |
|
"is_parallel": true, |
|
"self": 75.88668214302697 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 711.0981987309476, |
|
"count": 63711, |
|
"self": 2.4343279908746354, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 153.22679905207133, |
|
"count": 63711, |
|
"self": 153.02374417107103, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20305488100029834, |
|
"count": 2, |
|
"self": 0.20305488100029834 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 555.4370716880017, |
|
"count": 447, |
|
"self": 212.6245376719703, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 342.81253401603135, |
|
"count": 22806, |
|
"self": 342.81253401603135 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.1600031737471e-07, |
|
"count": 1, |
|
"self": 9.1600031737471e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09668497500024387, |
|
"count": 1, |
|
"self": 0.0015000450002844445, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09518492999995942, |
|
"count": 1, |
|
"self": 0.09518492999995942 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |