|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.8238424062728882, |
|
"min": 0.5983486175537109, |
|
"max": 1.4793857336044312, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 24675.728515625, |
|
"min": 17921.73828125, |
|
"max": 44878.64453125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479971.0, |
|
"min": 29952.0, |
|
"max": 479971.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479971.0, |
|
"min": 29952.0, |
|
"max": 479971.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.03393407538533211, |
|
"min": -0.11449132114648819, |
|
"max": 0.06466787308454514, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 8.245980262756348, |
|
"min": -27.706899642944336, |
|
"max": 15.326286315917969, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.004330315627157688, |
|
"min": -0.004330315627157688, |
|
"max": 0.22298245131969452, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -1.0522667169570923, |
|
"min": -1.0522667169570923, |
|
"max": 52.846839904785156, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06582760475465052, |
|
"min": 0.06582760475465052, |
|
"max": 0.07190233596700106, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9215864665651072, |
|
"min": 0.49718271729592556, |
|
"max": 1.0425069393685966, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.004342993218545286, |
|
"min": 0.0006843273065821146, |
|
"max": 0.005363659234896699, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.060801905059634, |
|
"min": 0.0063687238930104015, |
|
"max": 0.06255148644879013, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.070832166868571e-05, |
|
"min": 2.070832166868571e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00028991650336159994, |
|
"min": 0.00028991650336159994, |
|
"max": 0.002852871349043, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10690274285714285, |
|
"min": 0.10690274285714285, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4966384, |
|
"min": 1.3382272, |
|
"max": 2.3383966, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0006995840114285714, |
|
"min": 0.0006995840114285714, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00979417616, |
|
"min": 0.00979417616, |
|
"max": 0.0951306043, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.016969839110970497, |
|
"min": 0.016969839110970497, |
|
"max": 0.3948346674442291, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.23757773637771606, |
|
"min": 0.23757773637771606, |
|
"max": 2.7638425827026367, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 900.1818181818181, |
|
"min": 852.1351351351351, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29706.0, |
|
"min": 15984.0, |
|
"max": 32142.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.2945758043365045, |
|
"min": -1.0000000521540642, |
|
"max": -0.17778240911224308, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -9.721001543104649, |
|
"min": -32.000001668930054, |
|
"max": -6.044601909816265, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.2945758043365045, |
|
"min": -1.0000000521540642, |
|
"max": -0.17778240911224308, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -9.721001543104649, |
|
"min": -32.000001668930054, |
|
"max": -6.044601909816265, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.16064053057043842, |
|
"min": 0.16064053057043842, |
|
"max": 8.704850730486214, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.301137508824468, |
|
"min": 5.301137508824468, |
|
"max": 139.27761168777943, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657688449", |
|
"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": "1657689431" |
|
}, |
|
"total": 981.481013503, |
|
"count": 1, |
|
"self": 0.4849008919999278, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04234659999997348, |
|
"count": 1, |
|
"self": 0.04234659999997348 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 980.9537660110001, |
|
"count": 1, |
|
"self": 0.7118365039901846, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.093847574999927, |
|
"count": 1, |
|
"self": 10.093847574999927 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 970.0519258690099, |
|
"count": 31562, |
|
"self": 0.7559808919854731, |
|
"children": { |
|
"env_step": { |
|
"total": 609.220171189016, |
|
"count": 31562, |
|
"self": 555.4903335260225, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 53.36380215199665, |
|
"count": 31562, |
|
"self": 2.3488455790030685, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 51.01495657299358, |
|
"count": 31301, |
|
"self": 17.526318946007677, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 33.488637626985906, |
|
"count": 31301, |
|
"self": 33.488637626985906 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.3660355109968805, |
|
"count": 31562, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 978.865999423011, |
|
"count": 31562, |
|
"is_parallel": true, |
|
"self": 473.5258167499974, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007647147000056975, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004001559000016641, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003645588000040334, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003645588000040334 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04716679300008764, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000538208000079976, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004840750000312255, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004840750000312255 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04452872499996374, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04452872499996374 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016157850000126928, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043266899979244045, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011831160002202523, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011831160002202523 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 505.3401826730136, |
|
"count": 31561, |
|
"is_parallel": true, |
|
"self": 14.157218159027138, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.600098747987545, |
|
"count": 31561, |
|
"is_parallel": true, |
|
"self": 11.600098747987545 |
|
}, |
|
"communicator.exchange": { |
|
"total": 432.9098563040012, |
|
"count": 31561, |
|
"is_parallel": true, |
|
"self": 432.9098563040012 |
|
}, |
|
"steps_from_proto": { |
|
"total": 46.67300946199771, |
|
"count": 31561, |
|
"is_parallel": true, |
|
"self": 11.6029381770403, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 35.07007128495741, |
|
"count": 252488, |
|
"is_parallel": true, |
|
"self": 35.07007128495741 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 360.0757737880084, |
|
"count": 31562, |
|
"self": 1.212380208996251, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 82.00099711201199, |
|
"count": 31562, |
|
"self": 81.89295775001199, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10803936199999953, |
|
"count": 1, |
|
"self": 0.10803936199999953 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 276.86239646700017, |
|
"count": 211, |
|
"self": 109.21426200999713, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 167.64813445700304, |
|
"count": 11391, |
|
"self": 167.64813445700304 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.526000005469541e-06, |
|
"count": 1, |
|
"self": 1.526000005469541e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09615453700007492, |
|
"count": 1, |
|
"self": 0.00159229700011565, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09456223999995927, |
|
"count": 1, |
|
"self": 0.09456223999995927 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |