|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5920994281768799, |
|
"min": 0.5920994281768799, |
|
"max": 1.396640419960022, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 17772.45703125, |
|
"min": 17772.45703125, |
|
"max": 42368.484375, |
|
"count": 3 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 89895.0, |
|
"min": 29952.0, |
|
"max": 89895.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 89895.0, |
|
"min": 29952.0, |
|
"max": 89895.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.08060117810964584, |
|
"min": -0.08060117810964584, |
|
"max": 0.1492552012205124, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -19.50548553466797, |
|
"min": -19.50548553466797, |
|
"max": 35.37348175048828, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.910521388053894, |
|
"min": 0.910521388053894, |
|
"max": 1.4801007509231567, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 220.34617614746094, |
|
"min": 220.34617614746094, |
|
"max": 356.70428466796875, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.04922671732786335, |
|
"min": 0.04922671732786335, |
|
"max": 0.05336748282426961, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.5907206079343602, |
|
"min": 0.3735723797698873, |
|
"max": 0.5907206079343602, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.002812625459016786, |
|
"min": 0.002812625459016786, |
|
"max": 0.058140459392761475, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.03375150550820143, |
|
"min": 0.03375150550820143, |
|
"max": 0.40698321574933033, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.774157408616665e-05, |
|
"min": 7.774157408616665e-05, |
|
"max": 0.0002515063018788571, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0009328988890339999, |
|
"min": 0.0009328988890339999, |
|
"max": 0.0017605441131519997, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.12591383333333336, |
|
"min": 0.12591383333333336, |
|
"max": 0.1838354285714286, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5109660000000003, |
|
"min": 1.2868480000000002, |
|
"max": 1.5565020000000003, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0025987919500000006, |
|
"min": 0.0025987919500000006, |
|
"max": 0.008385159314285715, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.031185503400000005, |
|
"min": 0.031185503400000005, |
|
"max": 0.0586961152, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.12982051074504852, |
|
"min": 0.12982051074504852, |
|
"max": 0.4058314263820648, |
|
"count": 3 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 1.557846188545227, |
|
"min": 1.557846188545227, |
|
"max": 2.840820074081421, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 962.030303030303, |
|
"min": 962.030303030303, |
|
"max": 999.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31747.0, |
|
"min": 15984.0, |
|
"max": 31843.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.7204667153683576, |
|
"min": -1.0000000521540642, |
|
"max": -0.7204667153683576, |
|
"count": 3 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -23.7754016071558, |
|
"min": -27.873001739382744, |
|
"max": -16.000000834465027, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.7204667153683576, |
|
"min": -1.0000000521540642, |
|
"max": -0.7204667153683576, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -23.7754016071558, |
|
"min": -27.873001739382744, |
|
"max": -16.000000834465027, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 7.310272389289104, |
|
"min": 7.310272389289104, |
|
"max": 37.97674008458853, |
|
"count": 3 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 241.23898884654045, |
|
"min": 241.23898884654045, |
|
"max": 607.6278413534164, |
|
"count": 3 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1692017717", |
|
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
|
"command_line_arguments": "/home/victor/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --force", |
|
"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": "1692017912" |
|
}, |
|
"total": 195.31421026000044, |
|
"count": 1, |
|
"self": 0.3698744060006902, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.020221199999923556, |
|
"count": 1, |
|
"self": 0.020221199999923556 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 194.92411465399982, |
|
"count": 1, |
|
"self": 0.11492089701278019, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.843547811000008, |
|
"count": 1, |
|
"self": 5.843547811000008 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 188.84464944398724, |
|
"count": 6309, |
|
"self": 0.107466295982249, |
|
"children": { |
|
"env_step": { |
|
"total": 118.0586339260035, |
|
"count": 6309, |
|
"self": 98.41974282002502, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 19.56722700800401, |
|
"count": 6309, |
|
"self": 0.40011209500471523, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 19.167114912999295, |
|
"count": 6297, |
|
"self": 19.167114912999295 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.07166409797446249, |
|
"count": 6309, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 194.55289205097688, |
|
"count": 6309, |
|
"is_parallel": true, |
|
"self": 103.75594365197367, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0013616999999612744, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004546000000118511, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0009070999999494234, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0009070999999494234 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.03046879999965313, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00023869999995440594, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0002528999998503423, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002528999998503423 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.028661299999839684, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.028661299999839684 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0013159000000086962, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00026789999992615776, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010480000000825385, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010480000000825385 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 90.79694839900321, |
|
"count": 6308, |
|
"is_parallel": true, |
|
"self": 1.5050858869885815, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 1.172996385992974, |
|
"count": 6308, |
|
"is_parallel": true, |
|
"self": 1.172996385992974 |
|
}, |
|
"communicator.exchange": { |
|
"total": 83.50352456999826, |
|
"count": 6308, |
|
"is_parallel": true, |
|
"self": 83.50352456999826 |
|
}, |
|
"steps_from_proto": { |
|
"total": 4.615341556023395, |
|
"count": 6308, |
|
"is_parallel": true, |
|
"self": 1.0762646860112, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 3.5390768700121953, |
|
"count": 50464, |
|
"is_parallel": true, |
|
"self": 3.5390768700121953 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 70.6785492220015, |
|
"count": 6309, |
|
"self": 0.15120609997120482, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 9.888434483030323, |
|
"count": 6309, |
|
"self": 9.888434483030323 |
|
}, |
|
"_update_policy": { |
|
"total": 60.638908638999965, |
|
"count": 34, |
|
"self": 34.277911250998386, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 26.36099738800158, |
|
"count": 1910, |
|
"self": 26.36099738800158 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 6.000000212225132e-07, |
|
"count": 1, |
|
"self": 6.000000212225132e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.12099590199977683, |
|
"count": 1, |
|
"self": 0.0012509999996836996, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11974490200009313, |
|
"count": 1, |
|
"self": 0.11974490200009313 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |