|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5701867341995239, |
|
"min": 0.5577734708786011, |
|
"max": 1.4442542791366577, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 17087.35546875, |
|
"min": 16849.2421875, |
|
"max": 43812.8984375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989874.0, |
|
"min": 29952.0, |
|
"max": 989874.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989874.0, |
|
"min": 29952.0, |
|
"max": 989874.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.2854127287864685, |
|
"min": -0.11483945697546005, |
|
"max": 0.30683058500289917, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 73.35107421875, |
|
"min": -27.56147003173828, |
|
"max": 80.08277893066406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0178825743496418, |
|
"min": 0.006014855112880468, |
|
"max": 0.19324935972690582, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.595821380615234, |
|
"min": 1.4676246643066406, |
|
"max": 46.573097229003906, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0658754076929264, |
|
"min": 0.06311386663652402, |
|
"max": 0.0728761087388695, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9222557077009695, |
|
"min": 0.5029159414005899, |
|
"max": 1.0460020648509576, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.013314705687662354, |
|
"min": 9.644210114787467e-05, |
|
"max": 0.013314705687662354, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.18640587962727295, |
|
"min": 0.0012537473149223707, |
|
"max": 0.18640587962727295, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.23661187354286e-06, |
|
"min": 7.23661187354286e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010131256622960004, |
|
"min": 0.00010131256622960004, |
|
"max": 0.0035069834310055997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10241217142857141, |
|
"min": 0.10241217142857141, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4337703999999998, |
|
"min": 1.3886848, |
|
"max": 2.5689944000000007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025097592571428584, |
|
"min": 0.00025097592571428584, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035136629600000017, |
|
"min": 0.0035136629600000017, |
|
"max": 0.11692254056000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01051486935466528, |
|
"min": 0.01051486935466528, |
|
"max": 0.3340687155723572, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.14720816910266876, |
|
"min": 0.14720816910266876, |
|
"max": 2.3384809494018555, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 521.4909090909091, |
|
"min": 521.4909090909091, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28682.0, |
|
"min": 15984.0, |
|
"max": 33084.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.2218856836802192, |
|
"min": -1.0000000521540642, |
|
"max": 1.2218856836802192, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 68.42559828609228, |
|
"min": -31.996801659464836, |
|
"max": 68.42559828609228, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.2218856836802192, |
|
"min": -1.0000000521540642, |
|
"max": 1.2218856836802192, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 68.42559828609228, |
|
"min": -31.996801659464836, |
|
"max": 68.42559828609228, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.058433902971695977, |
|
"min": 0.058433902971695977, |
|
"max": 6.574957312084734, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.2722985664149746, |
|
"min": 3.2722985664149746, |
|
"max": 105.19931699335575, |
|
"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": "1673923388", |
|
"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": "1673925360" |
|
}, |
|
"total": 1972.0636223950005, |
|
"count": 1, |
|
"self": 0.4374367720010923, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11767241699999431, |
|
"count": 1, |
|
"self": 0.11767241699999431 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1971.5085132059994, |
|
"count": 1, |
|
"self": 1.1478751140457462, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.475218049999967, |
|
"count": 1, |
|
"self": 6.475218049999967 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1963.7937218979541, |
|
"count": 63311, |
|
"self": 1.2736565529608015, |
|
"children": { |
|
"env_step": { |
|
"total": 1296.2222433729507, |
|
"count": 63311, |
|
"self": 1194.7134055189267, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 100.77443560203164, |
|
"count": 63311, |
|
"self": 4.116283777042554, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 96.65815182498909, |
|
"count": 62570, |
|
"self": 32.61574064300066, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 64.04241118198843, |
|
"count": 62570, |
|
"self": 64.04241118198843 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7344022519923783, |
|
"count": 63311, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1967.1867038701444, |
|
"count": 63311, |
|
"is_parallel": true, |
|
"self": 866.1668635691944, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001790995000192197, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006118709998190752, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011791240003731218, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011791240003731218 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.051189886999964074, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004911470000479312, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004604999999173742, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004604999999173742 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0486493309999787, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0486493309999787 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015889090000200667, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00041670500013424316, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011722039998858236, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011722039998858236 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1101.01984030095, |
|
"count": 63310, |
|
"is_parallel": true, |
|
"self": 27.92841221577737, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.40749529709956, |
|
"count": 63310, |
|
"is_parallel": true, |
|
"self": 22.40749529709956 |
|
}, |
|
"communicator.exchange": { |
|
"total": 951.6313901430331, |
|
"count": 63310, |
|
"is_parallel": true, |
|
"self": 951.6313901430331 |
|
}, |
|
"steps_from_proto": { |
|
"total": 99.05254264503992, |
|
"count": 63310, |
|
"is_parallel": true, |
|
"self": 21.250573603167595, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 77.80196904187233, |
|
"count": 506480, |
|
"is_parallel": true, |
|
"self": 77.80196904187233 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 666.2978219720426, |
|
"count": 63311, |
|
"self": 2.0983243771624984, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 143.53914677387502, |
|
"count": 63311, |
|
"self": 143.34324369887509, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.19590307499993287, |
|
"count": 2, |
|
"self": 0.19590307499993287 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 520.6603508210051, |
|
"count": 446, |
|
"self": 198.95419894697352, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 321.70615187403155, |
|
"count": 22788, |
|
"self": 321.70615187403155 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0339999789721332e-06, |
|
"count": 1, |
|
"self": 1.0339999789721332e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09169710999958625, |
|
"count": 1, |
|
"self": 0.0017910799988385406, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0899060300007477, |
|
"count": 1, |
|
"self": 0.0899060300007477 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |