|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.39058181643486023, |
|
"min": 0.3880576491355896, |
|
"max": 1.459553837776184, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11667.4599609375, |
|
"min": 11561.013671875, |
|
"max": 44277.0234375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989896.0, |
|
"min": 29952.0, |
|
"max": 989896.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989896.0, |
|
"min": 29952.0, |
|
"max": 989896.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6784823536872864, |
|
"min": -0.12487329542636871, |
|
"max": 0.7192080616950989, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 196.7598876953125, |
|
"min": -29.594970703125, |
|
"max": 210.34275817871094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.05983000621199608, |
|
"min": -0.0071897488087415695, |
|
"max": 0.4392924904823303, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 17.3507022857666, |
|
"min": -2.0778374671936035, |
|
"max": 104.11231994628906, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06786776401124718, |
|
"min": 0.06559916276490271, |
|
"max": 0.07411818040224413, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9501486961574604, |
|
"min": 0.5076876772964378, |
|
"max": 1.111772706033662, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015238492379596989, |
|
"min": 0.0013708012818940986, |
|
"max": 0.017221679560385554, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21333889331435785, |
|
"min": 0.009595608973258691, |
|
"max": 0.24746541722561227, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.51835463677143e-06, |
|
"min": 7.51835463677143e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010525696491480002, |
|
"min": 0.00010525696491480002, |
|
"max": 0.0036366340877887005, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10250608571428572, |
|
"min": 0.10250608571428572, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4350852, |
|
"min": 1.3691136000000002, |
|
"max": 2.6625041000000005, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026035796285714294, |
|
"min": 0.00026035796285714294, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036450114800000008, |
|
"min": 0.0036450114800000008, |
|
"max": 0.12123990887, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010167197324335575, |
|
"min": 0.010167197324335575, |
|
"max": 0.35221976041793823, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1423407644033432, |
|
"min": 0.1423407644033432, |
|
"max": 2.465538263320923, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 268.9633027522936, |
|
"min": 262.9824561403509, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29317.0, |
|
"min": 15984.0, |
|
"max": 33204.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.694328427793236, |
|
"min": -1.0000000521540642, |
|
"max": 1.7205575053802633, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 184.68179862946272, |
|
"min": -32.000001668930054, |
|
"max": 194.42299810796976, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.694328427793236, |
|
"min": -1.0000000521540642, |
|
"max": 1.7205575053802633, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 184.68179862946272, |
|
"min": -32.000001668930054, |
|
"max": 194.42299810796976, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.02838406372476805, |
|
"min": 0.02838406372476805, |
|
"max": 6.668863368220627, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.0938629459997173, |
|
"min": 2.9652488683350384, |
|
"max": 106.70181389153004, |
|
"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": "1678862713", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=PyramidsTraining --no-graphics", |
|
"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": "1678864967" |
|
}, |
|
"total": 2253.5439232890003, |
|
"count": 1, |
|
"self": 0.5243075670005055, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11956333800003449, |
|
"count": 1, |
|
"self": 0.11956333800003449 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2252.900052384, |
|
"count": 1, |
|
"self": 1.5161924299227394, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.957519892000164, |
|
"count": 1, |
|
"self": 5.957519892000164 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2245.336043402077, |
|
"count": 64369, |
|
"self": 1.5377081790502416, |
|
"children": { |
|
"env_step": { |
|
"total": 1621.539504991996, |
|
"count": 64369, |
|
"self": 1510.54474936103, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 110.11567169498858, |
|
"count": 64369, |
|
"self": 4.764507346020309, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 105.35116434896827, |
|
"count": 62558, |
|
"self": 105.35116434896827 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8790839359774054, |
|
"count": 64369, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2248.005987673998, |
|
"count": 64369, |
|
"is_parallel": true, |
|
"self": 856.1903389009931, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0018182260000685346, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005633139999190462, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012549120001494884, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012549120001494884 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04511078399991675, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005103419998704339, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004311229999984789, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004311229999984789 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.042602344999977504, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.042602344999977504 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015669740000703314, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003467910003109864, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001220182999759345, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001220182999759345 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1391.8156487730048, |
|
"count": 64368, |
|
"is_parallel": true, |
|
"self": 31.09530913895992, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.877593181041675, |
|
"count": 64368, |
|
"is_parallel": true, |
|
"self": 22.877593181041675 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1245.3979681169621, |
|
"count": 64368, |
|
"is_parallel": true, |
|
"self": 1245.3979681169621 |
|
}, |
|
"steps_from_proto": { |
|
"total": 92.44477833604105, |
|
"count": 64368, |
|
"is_parallel": true, |
|
"self": 20.102412394214298, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 72.34236594182676, |
|
"count": 514944, |
|
"is_parallel": true, |
|
"self": 72.34236594182676 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 622.258830231031, |
|
"count": 64369, |
|
"self": 2.7872713510278118, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 115.75890168100545, |
|
"count": 64369, |
|
"self": 115.56105047700589, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19785120399956213, |
|
"count": 2, |
|
"self": 0.19785120399956213 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 503.7126571989977, |
|
"count": 454, |
|
"self": 318.65432485598967, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 185.05833234300803, |
|
"count": 22845, |
|
"self": 185.05833234300803 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.540000635548495e-07, |
|
"count": 1, |
|
"self": 8.540000635548495e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09029580600008558, |
|
"count": 1, |
|
"self": 0.0014374019997376308, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08885840400034795, |
|
"count": 1, |
|
"self": 0.08885840400034795 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |