|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5178590416908264, |
|
"min": 0.5178590416908264, |
|
"max": 1.4791070222854614, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 15660.056640625, |
|
"min": 15660.056640625, |
|
"max": 44870.19140625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989911.0, |
|
"min": 29952.0, |
|
"max": 989911.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989911.0, |
|
"min": 29952.0, |
|
"max": 989911.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5129061341285706, |
|
"min": -0.1785585731267929, |
|
"max": 0.5249461531639099, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 142.58790588378906, |
|
"min": -42.318382263183594, |
|
"max": 143.8352508544922, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.034320034086704254, |
|
"min": 0.0032990809995681047, |
|
"max": 0.33800482749938965, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 9.540969848632812, |
|
"min": 0.8709573745727539, |
|
"max": 80.10714721679688, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07042659121465736, |
|
"min": 0.06582088230623855, |
|
"max": 0.07318164310546175, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.985972277005203, |
|
"min": 0.49999001812980637, |
|
"max": 1.0653140756036792, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01655551698162786, |
|
"min": 0.000101875604966783, |
|
"max": 0.01655551698162786, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23177723774279005, |
|
"min": 0.001324382864568179, |
|
"max": 0.23177723774279005, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.640497453199997e-06, |
|
"min": 7.640497453199997e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010696696434479997, |
|
"min": 0.00010696696434479997, |
|
"max": 0.0033730825756391994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10254680000000001, |
|
"min": 0.10254680000000001, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4356552, |
|
"min": 1.3886848, |
|
"max": 2.4424844, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026442531999999996, |
|
"min": 0.00026442531999999996, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037019544799999993, |
|
"min": 0.0037019544799999993, |
|
"max": 0.11245364392, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007045875769108534, |
|
"min": 0.007004129700362682, |
|
"max": 0.3400173485279083, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.0986422598361969, |
|
"min": 0.0980578139424324, |
|
"max": 2.3801214694976807, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 367.07954545454544, |
|
"min": 367.07954545454544, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 32303.0, |
|
"min": 15984.0, |
|
"max": 32737.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.544608973803815, |
|
"min": -1.0000000521540642, |
|
"max": 1.5707209630880827, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 137.47019866853952, |
|
"min": -31.996001660823822, |
|
"max": 137.47019866853952, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.544608973803815, |
|
"min": -1.0000000521540642, |
|
"max": 1.5707209630880827, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 137.47019866853952, |
|
"min": -31.996001660823822, |
|
"max": 137.47019866853952, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.027025737970239442, |
|
"min": 0.027025737970239442, |
|
"max": 6.882999855093658, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.4052906793513102, |
|
"min": 2.1185081257717684, |
|
"max": 110.12799768149853, |
|
"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": "1664245096", |
|
"python_version": "3.7.14 (default, Sep 8 2022, 00:06:44) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1664247205" |
|
}, |
|
"total": 2108.903942203, |
|
"count": 1, |
|
"self": 0.5945470409997142, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.048080277000053684, |
|
"count": 1, |
|
"self": 0.048080277000053684 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2108.261314885, |
|
"count": 1, |
|
"self": 1.36308645895906, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.469163025999933, |
|
"count": 1, |
|
"self": 8.469163025999933 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2098.3306802760408, |
|
"count": 63576, |
|
"self": 1.5159093790757652, |
|
"children": { |
|
"env_step": { |
|
"total": 1380.7586062489456, |
|
"count": 63576, |
|
"self": 1273.3005204208716, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 106.73845873605887, |
|
"count": 63576, |
|
"self": 4.66526823398226, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 102.07319050207661, |
|
"count": 62569, |
|
"self": 35.24422547111044, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 66.82896503096617, |
|
"count": 62569, |
|
"self": 66.82896503096617 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7196270920151164, |
|
"count": 63576, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2104.1475046600526, |
|
"count": 63576, |
|
"is_parallel": true, |
|
"self": 933.4936933260606, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005384462000051826, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004044589000045562, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013398730000062642, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013398730000062642 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.047801032999927884, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000530345999891324, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00045821000003343215, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045821000003343215 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04512634100001378, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04512634100001378 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016861359999893466, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004239459999553219, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012621900000340247, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012621900000340247 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1170.653811333992, |
|
"count": 63575, |
|
"is_parallel": true, |
|
"self": 29.030829799908588, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.170460306024097, |
|
"count": 63575, |
|
"is_parallel": true, |
|
"self": 24.170460306024097 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1021.471080634004, |
|
"count": 63575, |
|
"is_parallel": true, |
|
"self": 1021.471080634004 |
|
}, |
|
"steps_from_proto": { |
|
"total": 95.98144059405524, |
|
"count": 63575, |
|
"is_parallel": true, |
|
"self": 23.819237060002934, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 72.16220353405231, |
|
"count": 508600, |
|
"is_parallel": true, |
|
"self": 72.16220353405231 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 716.0561646480194, |
|
"count": 63576, |
|
"self": 2.398137690065596, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 160.7673513769514, |
|
"count": 63576, |
|
"self": 160.55517184895166, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.21217952799975137, |
|
"count": 2, |
|
"self": 0.21217952799975137 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 552.8906755810024, |
|
"count": 447, |
|
"self": 219.8412136610134, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 333.04946191998897, |
|
"count": 22791, |
|
"self": 333.04946191998897 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0980002116411924e-06, |
|
"count": 1, |
|
"self": 1.0980002116411924e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09838402600007612, |
|
"count": 1, |
|
"self": 0.0017112509999606118, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09667277500011551, |
|
"count": 1, |
|
"self": 0.09667277500011551 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |