|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.46445223689079285, |
|
"min": 0.46445223689079285, |
|
"max": 1.4601253271102905, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14089.623046875, |
|
"min": 13889.1328125, |
|
"max": 44294.36328125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989966.0, |
|
"min": 29952.0, |
|
"max": 989966.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989966.0, |
|
"min": 29952.0, |
|
"max": 989966.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6161595582962036, |
|
"min": -0.08229049295186996, |
|
"max": 0.6161595582962036, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 174.37315368652344, |
|
"min": -19.749717712402344, |
|
"max": 174.37315368652344, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.016186917200684547, |
|
"min": -0.012584487907588482, |
|
"max": 0.3144819438457489, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.580897808074951, |
|
"min": -3.3852272033691406, |
|
"max": 74.53221893310547, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06358617169912793, |
|
"min": 0.06358617169912793, |
|
"max": 0.07411237038103427, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.890206403787791, |
|
"min": 0.5012172011505671, |
|
"max": 1.0813144370816492, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015463242687041027, |
|
"min": 0.0010827350301683477, |
|
"max": 0.018275435680975317, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21648539761857438, |
|
"min": 0.01407555539218852, |
|
"max": 0.25585609953365446, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.59138318385714e-06, |
|
"min": 7.59138318385714e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010627936457399997, |
|
"min": 0.00010627936457399997, |
|
"max": 0.0035076287307904998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10253042857142856, |
|
"min": 0.10253042857142856, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4354259999999999, |
|
"min": 1.3886848, |
|
"max": 2.5692095000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026278981428571425, |
|
"min": 0.00026278981428571425, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036790573999999996, |
|
"min": 0.0036790573999999996, |
|
"max": 0.11694402905000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.008616797626018524, |
|
"min": 0.008616797626018524, |
|
"max": 0.3396816551685333, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.12063516676425934, |
|
"min": 0.12063516676425934, |
|
"max": 2.3777716159820557, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 285.43564356435644, |
|
"min": 285.43564356435644, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28829.0, |
|
"min": 15984.0, |
|
"max": 33914.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.674956420713132, |
|
"min": -1.0000000521540642, |
|
"max": 1.674956420713132, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 169.17059849202633, |
|
"min": -28.793601594865322, |
|
"max": 169.17059849202633, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.674956420713132, |
|
"min": -1.0000000521540642, |
|
"max": 1.674956420713132, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 169.17059849202633, |
|
"min": -28.793601594865322, |
|
"max": 169.17059849202633, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.025628612634505717, |
|
"min": 0.025628612634505717, |
|
"max": 6.883682536892593, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.5884898760850774, |
|
"min": 2.5884898760850774, |
|
"max": 110.13892059028149, |
|
"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": "1673721861", |
|
"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": "1673723954" |
|
}, |
|
"total": 2093.18895876, |
|
"count": 1, |
|
"self": 0.4845020579996344, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.12475280099988595, |
|
"count": 1, |
|
"self": 0.12475280099988595 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2092.5797039010004, |
|
"count": 1, |
|
"self": 1.1723993110445008, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.411812143000134, |
|
"count": 1, |
|
"self": 6.411812143000134 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2084.906063933956, |
|
"count": 63902, |
|
"self": 1.2366710851406424, |
|
"children": { |
|
"env_step": { |
|
"total": 1416.409621916915, |
|
"count": 63902, |
|
"self": 1315.7847212509237, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 99.89295372097331, |
|
"count": 63902, |
|
"self": 4.127572898985363, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 95.76538082198795, |
|
"count": 62549, |
|
"self": 32.77021395393467, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 62.995166868053275, |
|
"count": 62549, |
|
"self": 62.995166868053275 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7319469450180804, |
|
"count": 63902, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2088.3009500779767, |
|
"count": 63902, |
|
"is_parallel": true, |
|
"self": 867.024746856936, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017838250000750122, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005835409992869245, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012002840007880877, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012002840007880877 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0490645120003137, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005546790002881608, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000476636000257713, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000476636000257713 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.046367821999865555, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.046367821999865555 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016653749999022693, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040621000016471953, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012591649997375498, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012591649997375498 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1221.2762032210408, |
|
"count": 63901, |
|
"is_parallel": true, |
|
"self": 27.910725856962472, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.387267051044546, |
|
"count": 63901, |
|
"is_parallel": true, |
|
"self": 22.387267051044546 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1070.6607257700111, |
|
"count": 63901, |
|
"is_parallel": true, |
|
"self": 1070.6607257700111 |
|
}, |
|
"steps_from_proto": { |
|
"total": 100.3174845430226, |
|
"count": 63901, |
|
"is_parallel": true, |
|
"self": 21.538350504764367, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 78.77913403825823, |
|
"count": 511208, |
|
"is_parallel": true, |
|
"self": 78.77913403825823 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 667.2597709319002, |
|
"count": 63902, |
|
"self": 2.132520272939928, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 143.83432847895983, |
|
"count": 63902, |
|
"self": 143.640551862959, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1937766160008323, |
|
"count": 2, |
|
"self": 0.1937766160008323 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 521.2929221800005, |
|
"count": 454, |
|
"self": 200.51002891994585, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 320.7828932600546, |
|
"count": 22800, |
|
"self": 320.7828932600546 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0559997463133186e-06, |
|
"count": 1, |
|
"self": 1.0559997463133186e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08942745700005617, |
|
"count": 1, |
|
"self": 0.0016225350000240724, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08780492200003209, |
|
"count": 1, |
|
"self": 0.08780492200003209 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |