|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.29111868143081665, |
|
"min": 0.28987595438957214, |
|
"max": 1.4414620399475098, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8663.6923828125, |
|
"min": 8663.6923828125, |
|
"max": 43728.19140625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989921.0, |
|
"min": 29952.0, |
|
"max": 989921.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989921.0, |
|
"min": 29952.0, |
|
"max": 989921.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6308280825614929, |
|
"min": -0.1255495548248291, |
|
"max": 0.6582887768745422, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 175.37020874023438, |
|
"min": -29.755245208740234, |
|
"max": 183.66256713867188, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0024349328596144915, |
|
"min": 0.0004303598834667355, |
|
"max": 0.3533593714237213, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.6769113540649414, |
|
"min": 0.11447572708129883, |
|
"max": 83.74617004394531, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07012577361813016, |
|
"min": 0.06352506810950061, |
|
"max": 0.07116443946637009, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9817608306538222, |
|
"min": 0.496838291394444, |
|
"max": 1.0642649706170035, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017663341398207084, |
|
"min": 0.0005794118880179994, |
|
"max": 0.017663341398207084, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2472867795748992, |
|
"min": 0.007532354544233991, |
|
"max": 0.2472867795748992, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.362268974514286e-06, |
|
"min": 7.362268974514286e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010307176564320001, |
|
"min": 0.00010307176564320001, |
|
"max": 0.0036351841882719996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10245405714285714, |
|
"min": 0.10245405714285714, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4343568, |
|
"min": 1.3886848, |
|
"max": 2.6117280000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002551603085714286, |
|
"min": 0.0002551603085714286, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00357224432, |
|
"min": 0.00357224432, |
|
"max": 0.12119162719999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011239634826779366, |
|
"min": 0.011239634826779366, |
|
"max": 0.5091322064399719, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15735489130020142, |
|
"min": 0.15735489130020142, |
|
"max": 3.563925266265869, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 293.5858585858586, |
|
"min": 293.5858585858586, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29065.0, |
|
"min": 15984.0, |
|
"max": 33335.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.665995936351593, |
|
"min": -1.0000000521540642, |
|
"max": 1.665995936351593, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 164.93359769880772, |
|
"min": -28.89500157535076, |
|
"max": 164.93359769880772, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.665995936351593, |
|
"min": -1.0000000521540642, |
|
"max": 1.665995936351593, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 164.93359769880772, |
|
"min": -28.89500157535076, |
|
"max": 164.93359769880772, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.033773766146770516, |
|
"min": 0.033773766146770516, |
|
"max": 10.679088339209557, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.3436028485302813, |
|
"min": 3.3436028485302813, |
|
"max": 170.8654134273529, |
|
"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": "1679268856", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1679271158" |
|
}, |
|
"total": 2301.2654896249996, |
|
"count": 1, |
|
"self": 0.4772586839994801, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10397257700014961, |
|
"count": 1, |
|
"self": 0.10397257700014961 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2300.684258364, |
|
"count": 1, |
|
"self": 1.444797903937797, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.927516594000053, |
|
"count": 1, |
|
"self": 5.927516594000053 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2293.2204486760625, |
|
"count": 63935, |
|
"self": 1.4767468960021688, |
|
"children": { |
|
"env_step": { |
|
"total": 1648.2363566100605, |
|
"count": 63935, |
|
"self": 1535.4445004610561, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 111.93982548501617, |
|
"count": 63935, |
|
"self": 5.012161195987574, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 106.9276642890286, |
|
"count": 62554, |
|
"self": 106.9276642890286 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8520306639882165, |
|
"count": 63935, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2295.330286142908, |
|
"count": 63935, |
|
"is_parallel": true, |
|
"self": 882.6113327379489, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001836743000012575, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006353330002184521, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001201409999794123, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001201409999794123 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05009516599989183, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000516645999823595, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004853049999837822, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004853049999837822 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04739130699999805, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04739130699999805 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001701908000086405, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00039395900034833176, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013079489997380733, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013079489997380733 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1412.718953404959, |
|
"count": 63934, |
|
"is_parallel": true, |
|
"self": 31.96615951096237, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.730393468996454, |
|
"count": 63934, |
|
"is_parallel": true, |
|
"self": 24.730393468996454 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1256.595337544049, |
|
"count": 63934, |
|
"is_parallel": true, |
|
"self": 1256.595337544049 |
|
}, |
|
"steps_from_proto": { |
|
"total": 99.4270628809511, |
|
"count": 63934, |
|
"is_parallel": true, |
|
"self": 21.41682609407735, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 78.01023678687375, |
|
"count": 511472, |
|
"is_parallel": true, |
|
"self": 78.01023678687375 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 643.50734517, |
|
"count": 63935, |
|
"self": 2.6267661289577973, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 124.99137863104556, |
|
"count": 63935, |
|
"self": 124.7770386000459, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21434003099966503, |
|
"count": 2, |
|
"self": 0.21434003099966503 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 515.8892004099966, |
|
"count": 455, |
|
"self": 329.35588162001636, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 186.53331878998029, |
|
"count": 22812, |
|
"self": 186.53331878998029 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.3269996088638436e-06, |
|
"count": 1, |
|
"self": 1.3269996088638436e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09149386299986872, |
|
"count": 1, |
|
"self": 0.0013222979996498907, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09017156500021883, |
|
"count": 1, |
|
"self": 0.09017156500021883 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |