|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7433567047119141, |
|
"min": 0.724847674369812, |
|
"max": 1.4182013273239136, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 22360.169921875, |
|
"min": 21861.40625, |
|
"max": 43022.5546875, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479916.0, |
|
"min": 29952.0, |
|
"max": 479916.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479916.0, |
|
"min": 29952.0, |
|
"max": 479916.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.041055046021938324, |
|
"min": -0.1149584949016571, |
|
"max": -0.017551442608237267, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -10.017431259155273, |
|
"min": -27.704998016357422, |
|
"max": -4.265000343322754, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.02648821473121643, |
|
"min": 0.024697335436940193, |
|
"max": 0.37810125946998596, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 6.4631242752075195, |
|
"min": 5.952057838439941, |
|
"max": 89.61000061035156, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06623994092672272, |
|
"min": 0.06511730348892872, |
|
"max": 0.07207408608453107, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9273591729741182, |
|
"min": 0.4976581523607046, |
|
"max": 1.0811112912679661, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.00382135175039212, |
|
"min": 0.0004337072131033828, |
|
"max": 0.00489009363191622, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.05349892450548968, |
|
"min": 0.006071900983447359, |
|
"max": 0.05349892450548968, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.057615028417143e-05, |
|
"min": 2.057615028417143e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0002880661039784, |
|
"min": 0.0002880661039784, |
|
"max": 0.003318515693828201, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10685868571428574, |
|
"min": 0.10685868571428574, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4960216000000004, |
|
"min": 1.3773696000000002, |
|
"max": 2.5061717999999997, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.000695182702857143, |
|
"min": 0.000695182702857143, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009732557840000001, |
|
"min": 0.009732557840000001, |
|
"max": 0.11064656281999997, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.023841289803385735, |
|
"min": 0.023841289803385735, |
|
"max": 0.4165857136249542, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.33377805352211, |
|
"min": 0.33377805352211, |
|
"max": 2.916100025177002, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 890.0571428571428, |
|
"min": 890.0571428571428, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31152.0, |
|
"min": 15984.0, |
|
"max": 33103.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.43337718759264265, |
|
"min": -1.0000000521540642, |
|
"max": -0.43337718759264265, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -15.168201565742493, |
|
"min": -28.10180176794529, |
|
"max": -15.168201565742493, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.43337718759264265, |
|
"min": -1.0000000521540642, |
|
"max": -0.43337718759264265, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -15.168201565742493, |
|
"min": -28.10180176794529, |
|
"max": -15.168201565742493, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.22296841906915818, |
|
"min": 0.22296841906915818, |
|
"max": 8.066823745146394, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.803894667420536, |
|
"min": 7.480509474873543, |
|
"max": 129.0691799223423, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1703884493", |
|
"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": "2.1.2+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1703885605" |
|
}, |
|
"total": 1111.6926424669998, |
|
"count": 1, |
|
"self": 0.4911350849997689, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.046279441000024235, |
|
"count": 1, |
|
"self": 0.046279441000024235 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1111.155227941, |
|
"count": 1, |
|
"self": 0.7133892669860415, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.9772558419999768, |
|
"count": 1, |
|
"self": 1.9772558419999768 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1108.375447604014, |
|
"count": 31615, |
|
"self": 0.751964456024325, |
|
"children": { |
|
"env_step": { |
|
"total": 791.4347067170061, |
|
"count": 31615, |
|
"self": 723.043241225969, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 67.95234010601098, |
|
"count": 31615, |
|
"self": 2.493416236009125, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 65.45892387000185, |
|
"count": 31307, |
|
"self": 65.45892387000185 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.4391253850260455, |
|
"count": 31615, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1108.4441916140077, |
|
"count": 31615, |
|
"is_parallel": true, |
|
"self": 448.8366315000012, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017864270000700344, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005619800001568365, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001224446999913198, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001224446999913198 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06053672699999879, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000637525000001915, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00050640199992813, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00050640199992813 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.057692947000077766, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.057692947000077766 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016998529999909806, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003345589998389187, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001365294000152062, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001365294000152062 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 659.6075601140064, |
|
"count": 31614, |
|
"is_parallel": true, |
|
"self": 17.874234671009845, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 13.26048501402397, |
|
"count": 31614, |
|
"is_parallel": true, |
|
"self": 13.26048501402397 |
|
}, |
|
"communicator.exchange": { |
|
"total": 576.1996261420059, |
|
"count": 31614, |
|
"is_parallel": true, |
|
"self": 576.1996261420059 |
|
}, |
|
"steps_from_proto": { |
|
"total": 52.27321428696678, |
|
"count": 31614, |
|
"is_parallel": true, |
|
"self": 10.683662930016226, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 41.58955135695055, |
|
"count": 252912, |
|
"is_parallel": true, |
|
"self": 41.58955135695055 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 316.1887764309836, |
|
"count": 31615, |
|
"self": 1.3516701149799246, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 64.67937221300122, |
|
"count": 31615, |
|
"self": 64.56751566100115, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11185655200006295, |
|
"count": 1, |
|
"self": 0.11185655200006295 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 250.15773410300244, |
|
"count": 220, |
|
"self": 148.65130827900907, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 101.50642582399337, |
|
"count": 11385, |
|
"self": 101.50642582399337 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.99999883788405e-07, |
|
"count": 1, |
|
"self": 9.99999883788405e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08913422800014814, |
|
"count": 1, |
|
"self": 0.0014078270000936755, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08772640100005447, |
|
"count": 1, |
|
"self": 0.08772640100005447 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |