|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4048716723918915, |
|
"min": 0.4048716723918915, |
|
"max": 1.3361148834228516, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12321.0546875, |
|
"min": 12161.798828125, |
|
"max": 40532.3828125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989972.0, |
|
"min": 29952.0, |
|
"max": 989972.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989972.0, |
|
"min": 29952.0, |
|
"max": 989972.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5534898638725281, |
|
"min": -0.10138043761253357, |
|
"max": 0.5964150428771973, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 154.97715759277344, |
|
"min": -24.43268585205078, |
|
"max": 165.42787170410156, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.008416467346251011, |
|
"min": -0.02113747037947178, |
|
"max": 0.37222594022750854, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.3566107749938965, |
|
"min": -5.495742321014404, |
|
"max": 88.21754455566406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06965881597508476, |
|
"min": 0.06428757949777957, |
|
"max": 0.07273983013527911, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9752234236511866, |
|
"min": 0.501044035172652, |
|
"max": 1.0779437077843457, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016229040028563412, |
|
"min": 0.0012669958243101006, |
|
"max": 0.016979255997162497, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22720656039988776, |
|
"min": 0.013936954067411106, |
|
"max": 0.25356806097746204, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.682861724792854e-06, |
|
"min": 7.682861724792854e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010756006414709997, |
|
"min": 0.00010756006414709997, |
|
"max": 0.0035086550304483993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10256092142857144, |
|
"min": 0.10256092142857144, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4358529000000002, |
|
"min": 1.3886848, |
|
"max": 2.5695515999999996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026583605071428567, |
|
"min": 0.00026583605071428567, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037217047099999995, |
|
"min": 0.0037217047099999995, |
|
"max": 0.11697820484000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011088361963629723, |
|
"min": 0.010981603525578976, |
|
"max": 0.4991123378276825, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.15523706376552582, |
|
"min": 0.1537424474954605, |
|
"max": 3.493786334991455, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 342.35632183908046, |
|
"min": 315.85714285714283, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29785.0, |
|
"min": 15984.0, |
|
"max": 32860.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.568243663201387, |
|
"min": -1.0000000521540642, |
|
"max": 1.6571999824190715, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 136.43719869852066, |
|
"min": -30.738001748919487, |
|
"max": 155.52179834246635, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.568243663201387, |
|
"min": -1.0000000521540642, |
|
"max": 1.6571999824190715, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 136.43719869852066, |
|
"min": -30.738001748919487, |
|
"max": 155.52179834246635, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03815298470994324, |
|
"min": 0.03633379267670272, |
|
"max": 10.16696454025805, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.3193096697650617, |
|
"min": 3.181184452609159, |
|
"max": 162.6714326441288, |
|
"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": "1707311203", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"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": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.2.0+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1707313829" |
|
}, |
|
"total": 2626.261400385, |
|
"count": 1, |
|
"self": 0.5471617309999601, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.058656939999991664, |
|
"count": 1, |
|
"self": 0.058656939999991664 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2625.655581714, |
|
"count": 1, |
|
"self": 1.944053845966664, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.9416027830000075, |
|
"count": 1, |
|
"self": 3.9416027830000075 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2619.669631490034, |
|
"count": 63909, |
|
"self": 2.076042585916639, |
|
"children": { |
|
"env_step": { |
|
"total": 1874.3471719769968, |
|
"count": 63909, |
|
"self": 1710.8646239969703, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 162.3127645380431, |
|
"count": 63909, |
|
"self": 5.878682258064941, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 156.43408227997816, |
|
"count": 62568, |
|
"self": 156.43408227997816 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.1697834419834408, |
|
"count": 63909, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2619.2375944230353, |
|
"count": 63909, |
|
"is_parallel": true, |
|
"self": 1052.4233976320356, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006058605000021089, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004486232000203927, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001572372999817162, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001572372999817162 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.053663136000068334, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006703070000639855, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005269289999887405, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005269289999887405 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05020550899996579, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05020550899996579 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0022603910000498217, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007394400003022383, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015209509997475834, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015209509997475834 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1566.8141967909996, |
|
"count": 63908, |
|
"is_parallel": true, |
|
"self": 43.73425522593175, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 27.982624278041612, |
|
"count": 63908, |
|
"is_parallel": true, |
|
"self": 27.982624278041612 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1377.0598216930111, |
|
"count": 63908, |
|
"is_parallel": true, |
|
"self": 1377.0598216930111 |
|
}, |
|
"steps_from_proto": { |
|
"total": 118.03749559401513, |
|
"count": 63908, |
|
"is_parallel": true, |
|
"self": 24.72353312523785, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 93.31396246877728, |
|
"count": 511264, |
|
"is_parallel": true, |
|
"self": 93.31396246877728 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 743.2464169271205, |
|
"count": 63909, |
|
"self": 3.5024060101685563, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 143.19992173995058, |
|
"count": 63909, |
|
"self": 142.91394920595064, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2859725339999386, |
|
"count": 2, |
|
"self": 0.2859725339999386 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 596.5440891770014, |
|
"count": 451, |
|
"self": 361.112324456996, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 235.4317647200054, |
|
"count": 22782, |
|
"self": 235.4317647200054 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.309997039963491e-07, |
|
"count": 1, |
|
"self": 9.309997039963491e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10029266399988046, |
|
"count": 1, |
|
"self": 0.0016730479997022485, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09861961600017821, |
|
"count": 1, |
|
"self": 0.09861961600017821 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |