|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4591062664985657, |
|
"min": 0.456118106842041, |
|
"max": 1.5057728290557861, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 13927.447265625, |
|
"min": 13515.69140625, |
|
"max": 45679.125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989951.0, |
|
"min": 29952.0, |
|
"max": 989951.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989951.0, |
|
"min": 29952.0, |
|
"max": 989951.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5590976476669312, |
|
"min": -0.09039661288261414, |
|
"max": 0.5924977660179138, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 155.98825073242188, |
|
"min": -21.78558349609375, |
|
"max": 162.7288360595703, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.020825471729040146, |
|
"min": -0.024494584649801254, |
|
"max": 0.2017737478017807, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -5.810306549072266, |
|
"min": -6.123646259307861, |
|
"max": 48.42570114135742, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06808953904103311, |
|
"min": 0.06506780430984407, |
|
"max": 0.07524592944075324, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9532535465744636, |
|
"min": 0.49465383786404366, |
|
"max": 1.0680342128890676, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014650845882507771, |
|
"min": 0.0005281179697287721, |
|
"max": 0.014800648616104459, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2051118423551088, |
|
"min": 0.004100512952453724, |
|
"max": 0.20720908062546242, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.666768873014282e-06, |
|
"min": 7.666768873014282e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010733476422219995, |
|
"min": 0.00010733476422219995, |
|
"max": 0.003507318230894, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10255555714285713, |
|
"min": 0.10255555714285713, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4357777999999999, |
|
"min": 1.3691136000000002, |
|
"max": 2.569106, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026530015857142845, |
|
"min": 0.00026530015857142845, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003714202219999998, |
|
"min": 0.003714202219999998, |
|
"max": 0.11693368940000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006720714271068573, |
|
"min": 0.006720714271068573, |
|
"max": 0.27758780121803284, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.09408999979496002, |
|
"min": 0.09408999979496002, |
|
"max": 1.9431145191192627, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 348.72222222222223, |
|
"min": 331.9759036144578, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31385.0, |
|
"min": 15984.0, |
|
"max": 32750.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5845866467389795, |
|
"min": -1.0000000521540642, |
|
"max": 1.5845866467389795, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 142.61279820650816, |
|
"min": -32.000001668930054, |
|
"max": 147.61859784275293, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5845866467389795, |
|
"min": -1.0000000521540642, |
|
"max": 1.5845866467389795, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 142.61279820650816, |
|
"min": -32.000001668930054, |
|
"max": 147.61859784275293, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.024349134189348358, |
|
"min": 0.024349134189348358, |
|
"max": 5.205910465680063, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.191422077041352, |
|
"min": 2.1033410527088563, |
|
"max": 83.294567450881, |
|
"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": "1674164105", |
|
"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 --force", |
|
"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": "1674166189" |
|
}, |
|
"total": 2083.24143596, |
|
"count": 1, |
|
"self": 0.42497292200005177, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0989104690000886, |
|
"count": 1, |
|
"self": 0.0989104690000886 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2082.717552569, |
|
"count": 1, |
|
"self": 1.5448716389860238, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.297730500999933, |
|
"count": 1, |
|
"self": 10.297730500999933 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2070.787890981014, |
|
"count": 63710, |
|
"self": 1.547684679030226, |
|
"children": { |
|
"env_step": { |
|
"total": 1410.7944304109922, |
|
"count": 63710, |
|
"self": 1291.8223829700205, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 118.00559979500679, |
|
"count": 63710, |
|
"self": 4.608467898033723, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 113.39713189697306, |
|
"count": 62556, |
|
"self": 37.91824100300619, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 75.47889089396688, |
|
"count": 62556, |
|
"self": 75.47889089396688 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9664476459649904, |
|
"count": 63710, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2077.6048766029667, |
|
"count": 63710, |
|
"is_parallel": true, |
|
"self": 895.9993045509577, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005642640000019128, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0033990109998285334, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0022436290001905945, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0022436290001905945 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.11996353400002135, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004788080000253103, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000422565000008035, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000422565000008035 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.1175965319999932, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.1175965319999932 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0014656289999948058, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00036322400001154165, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011024049999832641, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011024049999832641 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1181.605572052009, |
|
"count": 63709, |
|
"is_parallel": true, |
|
"self": 29.24651442309687, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.41014864896556, |
|
"count": 63709, |
|
"is_parallel": true, |
|
"self": 22.41014864896556 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1028.8439048119837, |
|
"count": 63709, |
|
"is_parallel": true, |
|
"self": 1028.8439048119837 |
|
}, |
|
"steps_from_proto": { |
|
"total": 101.10500416796265, |
|
"count": 63709, |
|
"is_parallel": true, |
|
"self": 23.093638650914386, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 78.01136551704826, |
|
"count": 509672, |
|
"is_parallel": true, |
|
"self": 78.01136551704826 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 658.4457758909914, |
|
"count": 63710, |
|
"self": 2.9135336979942394, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 145.45746141799793, |
|
"count": 63710, |
|
"self": 145.26999457099748, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1874668470004508, |
|
"count": 2, |
|
"self": 0.1874668470004508 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 510.0747807749992, |
|
"count": 440, |
|
"self": 189.83224610801733, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 320.2425346669819, |
|
"count": 22809, |
|
"self": 320.2425346669819 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.700003490957897e-07, |
|
"count": 1, |
|
"self": 8.700003490957897e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08705857799986916, |
|
"count": 1, |
|
"self": 0.0014780169999539794, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08558056099991518, |
|
"count": 1, |
|
"self": 0.08558056099991518 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |