|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.190852552652359, |
|
"min": 0.190852552652359, |
|
"max": 1.4776930809020996, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5789.703125, |
|
"min": 5789.703125, |
|
"max": 44827.296875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999907.0, |
|
"min": 29875.0, |
|
"max": 2999907.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999907.0, |
|
"min": 29875.0, |
|
"max": 2999907.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8032809495925903, |
|
"min": -0.10419106483459473, |
|
"max": 0.8913851976394653, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 245.80397033691406, |
|
"min": -25.005855560302734, |
|
"max": 269.1983337402344, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01829381287097931, |
|
"min": -0.058316152542829514, |
|
"max": 0.35751619935035706, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.597906589508057, |
|
"min": -15.162199974060059, |
|
"max": 84.73133850097656, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06659412673200547, |
|
"min": 0.0643410952643968, |
|
"max": 0.07499158209100812, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9323177742480766, |
|
"min": 0.599932656728065, |
|
"max": 1.1135934102440288, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.016800466954702557, |
|
"min": 4.7188830995680745e-05, |
|
"max": 0.016800466954702557, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23520653736583577, |
|
"min": 0.0006134548029438497, |
|
"max": 0.24805232497872604, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.459406656421433e-06, |
|
"min": 1.459406656421433e-06, |
|
"max": 0.0002982828880723708, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.043169318990006e-05, |
|
"min": 2.043169318990006e-05, |
|
"max": 0.003759127546957533, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10048643571428571, |
|
"min": 0.10048643571428571, |
|
"max": 0.19942762916666668, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4068101, |
|
"min": 1.4068101, |
|
"max": 2.6924080000000004, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.8594927857143e-05, |
|
"min": 5.8594927857143e-05, |
|
"max": 0.00994282015375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008203289900000021, |
|
"min": 0.0008203289900000021, |
|
"max": 0.12531894242, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.005474121309816837, |
|
"min": 0.005421524867415428, |
|
"max": 0.3707958459854126, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.07663770020008087, |
|
"min": 0.0760587528347969, |
|
"max": 2.966366767883301, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 208.64383561643837, |
|
"min": 201.45774647887325, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30462.0, |
|
"min": 16290.0, |
|
"max": 32824.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7758652939885653, |
|
"min": -0.9999600519736608, |
|
"max": 1.7977132760769838, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 261.0521982163191, |
|
"min": -30.997601605951786, |
|
"max": 261.0521982163191, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7758652939885653, |
|
"min": -0.9999600519736608, |
|
"max": 1.7977132760769838, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 261.0521982163191, |
|
"min": -30.997601605951786, |
|
"max": 261.0521982163191, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01208297944255292, |
|
"min": 0.01165229568458289, |
|
"max": 7.72331192475908, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.7761979780552792, |
|
"min": 1.6230957971565658, |
|
"max": 131.29630272090435, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1674244483", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"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": "1674250896" |
|
}, |
|
"total": 6413.5053127930005, |
|
"count": 1, |
|
"self": 0.37370159399961267, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1483111969998845, |
|
"count": 1, |
|
"self": 0.1483111969998845 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6412.983300002001, |
|
"count": 1, |
|
"self": 4.227269895247446, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.628078054999833, |
|
"count": 1, |
|
"self": 5.628078054999833 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6403.018641285754, |
|
"count": 194827, |
|
"self": 4.510763544407382, |
|
"children": { |
|
"env_step": { |
|
"total": 3928.891123245172, |
|
"count": 194827, |
|
"self": 3522.4936965011116, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 403.7743198919993, |
|
"count": 194827, |
|
"self": 15.311660703165217, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 388.4626591888341, |
|
"count": 187562, |
|
"self": 137.79051260383244, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 250.67214658500166, |
|
"count": 187562, |
|
"self": 250.67214658500166 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.623106852061028, |
|
"count": 194827, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6404.38730032729, |
|
"count": 194827, |
|
"is_parallel": true, |
|
"self": 3207.7228859144066, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00232741700006045, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007688670000334241, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015585500000270258, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015585500000270258 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04378473899987512, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003437779998876067, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005886379999537894, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005886379999537894 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04158878199996252, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04158878199996252 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0012635410000712, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003277290002188238, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0009358119998523762, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0009358119998523762 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3196.6644144128836, |
|
"count": 194826, |
|
"is_parallel": true, |
|
"self": 66.7227202963436, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 53.87475066277625, |
|
"count": 194826, |
|
"is_parallel": true, |
|
"self": 53.87475066277625 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2838.273514727004, |
|
"count": 194826, |
|
"is_parallel": true, |
|
"self": 2838.273514727004 |
|
}, |
|
"steps_from_proto": { |
|
"total": 237.7934287267601, |
|
"count": 194826, |
|
"is_parallel": true, |
|
"self": 61.241649386461404, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 176.5517793402987, |
|
"count": 1558608, |
|
"is_parallel": true, |
|
"self": 176.5517793402987 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2469.6167544961745, |
|
"count": 194827, |
|
"self": 7.22526182844922, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 533.7097957147307, |
|
"count": 194827, |
|
"self": 533.02035039273, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6894453220006653, |
|
"count": 6, |
|
"self": 0.6894453220006653 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1928.6816969529943, |
|
"count": 1389, |
|
"self": 680.729455620942, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1247.9522413320524, |
|
"count": 68433, |
|
"self": 1247.9522413320524 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.035999957821332e-06, |
|
"count": 1, |
|
"self": 1.035999957821332e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10930972999994992, |
|
"count": 1, |
|
"self": 0.0015776340005686507, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10773209599938127, |
|
"count": 1, |
|
"self": 0.10773209599938127 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |