|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5341572165489197, |
|
"min": 0.5341572165489197, |
|
"max": 1.469539999961853, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 16024.716796875, |
|
"min": 16024.716796875, |
|
"max": 44579.96484375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989898.0, |
|
"min": 29952.0, |
|
"max": 989898.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989898.0, |
|
"min": 29952.0, |
|
"max": 989898.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4251503050327301, |
|
"min": -0.20359113812446594, |
|
"max": 0.4761638641357422, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 113.9402847290039, |
|
"min": -48.2510986328125, |
|
"max": 129.99273681640625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.049929361790418625, |
|
"min": -0.02472783625125885, |
|
"max": 0.26592355966567993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 13.38106918334961, |
|
"min": -6.132503509521484, |
|
"max": 63.02388381958008, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06712919304678731, |
|
"min": 0.06357114401767265, |
|
"max": 0.07356631943945216, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9398087026550224, |
|
"min": 0.5149642360761651, |
|
"max": 1.0576008742974214, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01470986540473806, |
|
"min": 0.00032184125562160224, |
|
"max": 0.01671079702992713, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20593811566633283, |
|
"min": 0.00289657130059442, |
|
"max": 0.23395115841897982, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.552511768242855e-06, |
|
"min": 7.552511768242855e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010573516475539997, |
|
"min": 0.00010573516475539997, |
|
"max": 0.003507032630989199, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251747142857146, |
|
"min": 0.10251747142857146, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4352446000000003, |
|
"min": 1.3886848, |
|
"max": 2.569010799999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002614953957142857, |
|
"min": 0.0002614953957142857, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00366093554, |
|
"min": 0.00366093554, |
|
"max": 0.11692417892000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.008242675103247166, |
|
"min": 0.008242675103247166, |
|
"max": 0.3748420774936676, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11539745330810547, |
|
"min": 0.11539745330810547, |
|
"max": 2.623894453048706, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 420.09090909090907, |
|
"min": 363.5189873417722, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 27726.0, |
|
"min": 15984.0, |
|
"max": 32518.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4586514875744327, |
|
"min": -1.0000000521540642, |
|
"max": 1.6111544061310683, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 96.27099817991257, |
|
"min": -31.99920167028904, |
|
"max": 127.2811980843544, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4586514875744327, |
|
"min": -1.0000000521540642, |
|
"max": 1.6111544061310683, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 96.27099817991257, |
|
"min": -31.99920167028904, |
|
"max": 127.2811980843544, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03618221617216477, |
|
"min": 0.03334729493250466, |
|
"max": 7.795685742050409, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.388026267362875, |
|
"min": 2.388026267362875, |
|
"max": 124.73097187280655, |
|
"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": "1678171433", |
|
"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": "1678173737" |
|
}, |
|
"total": 2303.5275719290003, |
|
"count": 1, |
|
"self": 0.5246122500002457, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11387883899988083, |
|
"count": 1, |
|
"self": 0.11387883899988083 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2302.88908084, |
|
"count": 1, |
|
"self": 1.3703678440515432, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.534216340000057, |
|
"count": 1, |
|
"self": 6.534216340000057 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2294.8960864909495, |
|
"count": 63550, |
|
"self": 1.4550479949393775, |
|
"children": { |
|
"env_step": { |
|
"total": 1528.165041613981, |
|
"count": 63550, |
|
"self": 1407.6019427379924, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 119.7010100010325, |
|
"count": 63550, |
|
"self": 5.043603213082406, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 114.6574067879501, |
|
"count": 62551, |
|
"self": 39.122078027967746, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 75.53532875998235, |
|
"count": 62551, |
|
"self": 75.53532875998235 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8620888749560436, |
|
"count": 63550, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2297.6635041630548, |
|
"count": 63550, |
|
"is_parallel": true, |
|
"self": 1011.5827555870464, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0023695509999015485, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008520300002601289, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015175209996414196, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015175209996414196 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.10250682200012307, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005578970003625727, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005485120000230381, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005485120000230381 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0995777809998799, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0995777809998799 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001822631999857549, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046221400043577887, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013604179994217702, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013604179994217702 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1286.0807485760083, |
|
"count": 63549, |
|
"is_parallel": true, |
|
"self": 32.41453092417396, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.936271923925688, |
|
"count": 63549, |
|
"is_parallel": true, |
|
"self": 24.936271923925688 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1129.5655967409862, |
|
"count": 63549, |
|
"is_parallel": true, |
|
"self": 1129.5655967409862 |
|
}, |
|
"steps_from_proto": { |
|
"total": 99.1643489869225, |
|
"count": 63549, |
|
"is_parallel": true, |
|
"self": 24.224253969735855, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 74.94009501718665, |
|
"count": 508392, |
|
"is_parallel": true, |
|
"self": 74.94009501718665 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 765.2759968820292, |
|
"count": 63550, |
|
"self": 2.591107439159714, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 172.9253105208786, |
|
"count": 63550, |
|
"self": 172.73375930087923, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19155121999938274, |
|
"count": 2, |
|
"self": 0.19155121999938274 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 589.7595789219909, |
|
"count": 445, |
|
"self": 231.00271764996114, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 358.7568612720297, |
|
"count": 22791, |
|
"self": 358.7568612720297 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1739994079107419e-06, |
|
"count": 1, |
|
"self": 1.1739994079107419e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08840899099959643, |
|
"count": 1, |
|
"self": 0.0013298569992912235, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0870791340003052, |
|
"count": 1, |
|
"self": 0.0870791340003052 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |