|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.13367363810539246, |
|
"min": 0.12460928410291672, |
|
"max": 1.396437168121338, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4003.79296875, |
|
"min": 3734.291015625, |
|
"max": 42362.31640625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999876.0, |
|
"min": 29933.0, |
|
"max": 2999876.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999876.0, |
|
"min": 29933.0, |
|
"max": 2999876.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.842029333114624, |
|
"min": -0.17443805932998657, |
|
"max": 0.887333869934082, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 252.60879516601562, |
|
"min": -41.341819763183594, |
|
"max": 274.1861572265625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.021110884845256805, |
|
"min": -0.14295190572738647, |
|
"max": 0.29287469387054443, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -6.33326530456543, |
|
"min": -43.02852249145508, |
|
"max": 69.41130065917969, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07215591635565137, |
|
"min": 0.06462412136135667, |
|
"max": 0.07533751647861209, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0101828289791193, |
|
"min": 0.6502140919696758, |
|
"max": 1.0853925430371114, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017265026637407456, |
|
"min": 7.352458153976323e-05, |
|
"max": 0.017265026637407456, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2417103729237044, |
|
"min": 0.0010293441415566852, |
|
"max": 0.2417103729237044, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5377709160142874e-06, |
|
"min": 1.5377709160142874e-06, |
|
"max": 0.0002982628005790666, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.1528792824200023e-05, |
|
"min": 2.1528792824200023e-05, |
|
"max": 0.003937756987414401, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10051255714285715, |
|
"min": 0.10051255714285715, |
|
"max": 0.19942093333333336, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4071758, |
|
"min": 1.4071758, |
|
"max": 2.8125856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.120445857142865e-05, |
|
"min": 6.120445857142865e-05, |
|
"max": 0.009942151239999999, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008568624200000012, |
|
"min": 0.0008568624200000012, |
|
"max": 0.13127730144000002, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006371617317199707, |
|
"min": 0.006213414017111063, |
|
"max": 0.3691787123680115, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.0892026424407959, |
|
"min": 0.08698779344558716, |
|
"max": 3.322608470916748, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 213.75, |
|
"min": 201.10135135135135, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29070.0, |
|
"min": 16860.0, |
|
"max": 33391.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7862499932594158, |
|
"min": -0.9999375520274043, |
|
"max": 1.798898635281099, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 242.92999908328056, |
|
"min": -31.998001664876938, |
|
"max": 266.23699802160263, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7862499932594158, |
|
"min": -0.9999375520274043, |
|
"max": 1.798898635281099, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 242.92999908328056, |
|
"min": -31.998001664876938, |
|
"max": 266.23699802160263, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.014169845750981333, |
|
"min": 0.013199554409397565, |
|
"max": 7.490249448839356, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.9270990221334614, |
|
"min": 1.9270990221334614, |
|
"max": 127.33424063026905, |
|
"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": "1657271066", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1657277718" |
|
}, |
|
"total": 6651.672462271999, |
|
"count": 1, |
|
"self": 0.49205085700032214, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04116840099993624, |
|
"count": 1, |
|
"self": 0.04116840099993624 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6651.1392430139995, |
|
"count": 1, |
|
"self": 4.499848385020414, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.51917691199992, |
|
"count": 1, |
|
"self": 9.51917691199992 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6637.02703801098, |
|
"count": 195426, |
|
"self": 4.744238688845144, |
|
"children": { |
|
"env_step": { |
|
"total": 4528.1738454941715, |
|
"count": 195426, |
|
"self": 4207.10829446426, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 318.7088639567952, |
|
"count": 195426, |
|
"self": 13.671015595765311, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 305.0378483610299, |
|
"count": 187553, |
|
"self": 103.87044819700759, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 201.1674001640223, |
|
"count": 187553, |
|
"self": 201.1674001640223 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.3566870731157223, |
|
"count": 195426, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6639.470970110007, |
|
"count": 195426, |
|
"is_parallel": true, |
|
"self": 2741.0868724361253, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00517699099998481, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003927291999843874, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012496990001409358, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012496990001409358 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05812334400002328, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005841979999559044, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005286069999783649, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005286069999783649 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05517981700006658, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05517981700006658 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018307220000224333, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048700700006065745, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001343714999961776, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001343714999961776 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3898.384097673882, |
|
"count": 195425, |
|
"is_parallel": true, |
|
"self": 83.66255333288518, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 70.36719016214124, |
|
"count": 195425, |
|
"is_parallel": true, |
|
"self": 70.36719016214124 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3463.7464605358946, |
|
"count": 195425, |
|
"is_parallel": true, |
|
"self": 3463.7464605358946 |
|
}, |
|
"steps_from_proto": { |
|
"total": 280.60789364296136, |
|
"count": 195425, |
|
"is_parallel": true, |
|
"self": 70.15966988989567, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 210.4482237530657, |
|
"count": 1563400, |
|
"is_parallel": true, |
|
"self": 210.4482237530657 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2104.108953827963, |
|
"count": 195426, |
|
"self": 8.455526140973234, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 493.62854884399087, |
|
"count": 195426, |
|
"self": 493.05477139699053, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5737774470003387, |
|
"count": 6, |
|
"self": 0.5737774470003387 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1602.024878842999, |
|
"count": 1398, |
|
"self": 626.1527516740558, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 975.8721271689432, |
|
"count": 68442, |
|
"self": 975.8721271689432 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0499998097657226e-06, |
|
"count": 1, |
|
"self": 1.0499998097657226e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09317865599950892, |
|
"count": 1, |
|
"self": 0.0015544609987045988, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09162419500080432, |
|
"count": 1, |
|
"self": 0.09162419500080432 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |