|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4159446656703949, |
|
"min": 0.41105031967163086, |
|
"max": 1.463675618171692, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12405.1337890625, |
|
"min": 12377.546875, |
|
"max": 44402.0625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989935.0, |
|
"min": 29952.0, |
|
"max": 989935.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989935.0, |
|
"min": 29952.0, |
|
"max": 989935.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.48344939947128296, |
|
"min": -0.10961730778217316, |
|
"max": 0.48344939947128296, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 131.981689453125, |
|
"min": -26.417770385742188, |
|
"max": 131.981689453125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.018144985660910606, |
|
"min": -0.004240359179675579, |
|
"max": 0.36385050415992737, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.953580856323242, |
|
"min": -1.1321759223937988, |
|
"max": 87.68797302246094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06978499329948429, |
|
"min": 0.06485442905007706, |
|
"max": 0.07499388291837714, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.97698990619278, |
|
"min": 0.5249571804286399, |
|
"max": 1.0467561492405366, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014216497844902452, |
|
"min": 0.0002269950624827067, |
|
"max": 0.016620508005005485, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.19903096982863433, |
|
"min": 0.0031779308747578935, |
|
"max": 0.2326871120700768, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.476054650871424e-06, |
|
"min": 7.476054650871424e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010466476511219994, |
|
"min": 0.00010466476511219994, |
|
"max": 0.0035079650306784, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249198571428574, |
|
"min": 0.10249198571428574, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4348878000000003, |
|
"min": 1.3886848, |
|
"max": 2.5693216000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002589493728571428, |
|
"min": 0.0002589493728571428, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036252912199999992, |
|
"min": 0.0036252912199999992, |
|
"max": 0.11695522784, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.014533202163875103, |
|
"min": 0.014533202163875103, |
|
"max": 0.46606871485710144, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2034648358821869, |
|
"min": 0.2034648358821869, |
|
"max": 3.2624809741973877, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 399.7536231884058, |
|
"min": 399.7536231884058, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 27583.0, |
|
"min": 15984.0, |
|
"max": 33980.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4563058592817362, |
|
"min": -1.0000000521540642, |
|
"max": 1.4563058592817362, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 99.02879843115807, |
|
"min": -30.402601696550846, |
|
"max": 112.60359859466553, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4563058592817362, |
|
"min": -1.0000000521540642, |
|
"max": 1.4563058592817362, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 99.02879843115807, |
|
"min": -30.402601696550846, |
|
"max": 112.60359859466553, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.059970706661474915, |
|
"min": 0.059970706661474915, |
|
"max": 9.028556422330439, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.0780080529802945, |
|
"min": 4.0780080529802945, |
|
"max": 144.45690275728703, |
|
"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": "1674307925", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1674309838" |
|
}, |
|
"total": 1912.4648693149998, |
|
"count": 1, |
|
"self": 0.4439695269998083, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.09712158499996804, |
|
"count": 1, |
|
"self": 0.09712158499996804 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1911.923778203, |
|
"count": 1, |
|
"self": 1.223459255015996, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.046021311000004, |
|
"count": 1, |
|
"self": 6.046021311000004 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1904.573471472984, |
|
"count": 63531, |
|
"self": 1.2619779690433006, |
|
"children": { |
|
"env_step": { |
|
"total": 1272.3272957499833, |
|
"count": 63531, |
|
"self": 1169.8358402949186, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 101.68641193402323, |
|
"count": 63531, |
|
"self": 4.145382695960734, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 97.54102923806249, |
|
"count": 62564, |
|
"self": 32.69494480810772, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 64.84608442995477, |
|
"count": 62564, |
|
"self": 64.84608442995477 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.805043521041398, |
|
"count": 63531, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1907.8305869290218, |
|
"count": 63531, |
|
"is_parallel": true, |
|
"self": 833.4672959730124, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0022034160001567216, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009251310000308877, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001278285000125834, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001278285000125834 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04384563899998284, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046192699983294006, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00043083300010948733, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043083300010948733 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0414531960000204, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0414531960000204 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0014996830000200134, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003951570004119276, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011045259996080858, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011045259996080858 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1074.3632909560095, |
|
"count": 63530, |
|
"is_parallel": true, |
|
"self": 27.003584442031524, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 21.064239312068366, |
|
"count": 63530, |
|
"is_parallel": true, |
|
"self": 21.064239312068366 |
|
}, |
|
"communicator.exchange": { |
|
"total": 931.4067954829868, |
|
"count": 63530, |
|
"is_parallel": true, |
|
"self": 931.4067954829868 |
|
}, |
|
"steps_from_proto": { |
|
"total": 94.88867171892275, |
|
"count": 63530, |
|
"is_parallel": true, |
|
"self": 21.016305269017266, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 73.87236644990548, |
|
"count": 508240, |
|
"is_parallel": true, |
|
"self": 73.87236644990548 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 630.9841977539575, |
|
"count": 63531, |
|
"self": 2.3500413649676375, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 137.8419337369919, |
|
"count": 63531, |
|
"self": 137.66543594699215, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.17649778999975752, |
|
"count": 2, |
|
"self": 0.17649778999975752 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 490.7922226519979, |
|
"count": 448, |
|
"self": 186.19677571601483, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 304.5954469359831, |
|
"count": 22836, |
|
"self": 304.5954469359831 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 7.700000423938036e-07, |
|
"count": 1, |
|
"self": 7.700000423938036e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08082539399993038, |
|
"count": 1, |
|
"self": 0.0013563309998971818, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0794690630000332, |
|
"count": 1, |
|
"self": 0.0794690630000332 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |