|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3569423258304596, |
|
"min": 0.3569423258304596, |
|
"max": 1.4746330976486206, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 10622.603515625, |
|
"min": 10622.603515625, |
|
"max": 44734.46875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989934.0, |
|
"min": 29952.0, |
|
"max": 989934.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989934.0, |
|
"min": 29952.0, |
|
"max": 989934.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.40554696321487427, |
|
"min": -0.14670321345329285, |
|
"max": 0.4706757664680481, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 106.65885162353516, |
|
"min": -34.76866149902344, |
|
"max": 126.61177825927734, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.0045495848171412945, |
|
"min": -0.0045495848171412945, |
|
"max": 0.25074440240859985, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -1.1965408325195312, |
|
"min": -1.1965408325195312, |
|
"max": 59.426422119140625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06814846335392861, |
|
"min": 0.06275959842515841, |
|
"max": 0.07399084628480797, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0222269503089292, |
|
"min": 0.4851005819934586, |
|
"max": 1.0940490033330312, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01363182086449039, |
|
"min": 0.0010118964599019062, |
|
"max": 0.015477508004031346, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20447731296735586, |
|
"min": 0.007545239252673733, |
|
"max": 0.21668511205643884, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.515897494733334e-06, |
|
"min": 7.515897494733334e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011273846242100001, |
|
"min": 0.00011273846242100001, |
|
"max": 0.0036335314888228994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10250526666666668, |
|
"min": 0.10250526666666668, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5375790000000003, |
|
"min": 1.3691136000000002, |
|
"max": 2.6111771000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002602761400000001, |
|
"min": 0.0002602761400000001, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0039041421000000015, |
|
"min": 0.0039041421000000015, |
|
"max": 0.12113659229, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009283142164349556, |
|
"min": 0.009283142164349556, |
|
"max": 0.2695707380771637, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1392471343278885, |
|
"min": 0.13411398231983185, |
|
"max": 1.8869950771331787, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 410.875, |
|
"min": 382.1392405063291, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29583.0, |
|
"min": 15984.0, |
|
"max": 32371.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.4223972018808126, |
|
"min": -1.0000000521540642, |
|
"max": 1.4405923827162272, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 102.41259853541851, |
|
"min": -32.000001668930054, |
|
"max": 113.80679823458195, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.4223972018808126, |
|
"min": -1.0000000521540642, |
|
"max": 1.4405923827162272, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 102.41259853541851, |
|
"min": -32.000001668930054, |
|
"max": 113.80679823458195, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.039131969059477946, |
|
"min": 0.039131969059477946, |
|
"max": 5.096554284915328, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.8175017722824123, |
|
"min": 2.8175017722824123, |
|
"max": 81.54486855864525, |
|
"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": "1673444558", |
|
"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": "1673446600" |
|
}, |
|
"total": 2042.3718711020001, |
|
"count": 1, |
|
"self": 0.4746067269998093, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10942183099996328, |
|
"count": 1, |
|
"self": 0.10942183099996328 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2041.7878425440003, |
|
"count": 1, |
|
"self": 1.13619342614993, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.510633092999797, |
|
"count": 1, |
|
"self": 6.510633092999797 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2034.0497634288513, |
|
"count": 63678, |
|
"self": 1.1913426247469943, |
|
"children": { |
|
"env_step": { |
|
"total": 1370.4626225610673, |
|
"count": 63678, |
|
"self": 1270.7756676140934, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 98.94974638800068, |
|
"count": 63678, |
|
"self": 4.0518581009309855, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 94.89788828706969, |
|
"count": 62561, |
|
"self": 32.316950265092146, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 62.580938021977545, |
|
"count": 62561, |
|
"self": 62.580938021977545 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7372085589731796, |
|
"count": 63678, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2038.2262380288726, |
|
"count": 63678, |
|
"is_parallel": true, |
|
"self": 862.7297736628807, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001760930999807897, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005919409995840397, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011689900002238574, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011689900002238574 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04399581900042904, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000491171000248869, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004309040000407549, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004309040000407549 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04150152500005788, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04150152500005788 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015722190000815317, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000427639999998064, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011445790000834677, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011445790000834677 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1175.4964643659919, |
|
"count": 63677, |
|
"is_parallel": true, |
|
"self": 28.05835989913703, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.545035458977054, |
|
"count": 63677, |
|
"is_parallel": true, |
|
"self": 22.545035458977054 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1032.9946892349335, |
|
"count": 63677, |
|
"is_parallel": true, |
|
"self": 1032.9946892349335 |
|
}, |
|
"steps_from_proto": { |
|
"total": 91.89837977294428, |
|
"count": 63677, |
|
"is_parallel": true, |
|
"self": 20.982000310051717, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 70.91637946289256, |
|
"count": 509416, |
|
"is_parallel": true, |
|
"self": 70.91637946289256 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 662.395798243037, |
|
"count": 63678, |
|
"self": 2.180197372996645, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 141.78992880504302, |
|
"count": 63678, |
|
"self": 141.52560823304339, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2643205719996331, |
|
"count": 2, |
|
"self": 0.2643205719996331 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 518.4256720649973, |
|
"count": 450, |
|
"self": 200.06690263508563, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 318.3587694299117, |
|
"count": 22794, |
|
"self": 318.3587694299117 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.032999534800183e-06, |
|
"count": 1, |
|
"self": 1.032999534800183e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09125156299978698, |
|
"count": 1, |
|
"self": 0.0015541779994237004, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08969738500036328, |
|
"count": 1, |
|
"self": 0.08969738500036328 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |