{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37221190333366394, "min": 0.37221190333366394, "max": 1.4548053741455078, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11208.044921875, "min": 11208.044921875, "max": 44132.9765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5196493268013, "min": -0.146745502948761, "max": 0.5714281797409058, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.903564453125, "min": -35.365665435791016, "max": 158.2855987548828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026558618992567062, "min": 0.006787791382521391, "max": 0.3601658344268799, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.303620338439941, "min": 1.8530670404434204, "max": 87.1601333618164, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06905311138516047, "min": 0.0656891417304342, "max": 0.07295907923856053, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9667435593922467, "min": 0.48912309593656206, "max": 1.0518215575333065, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014608238636615816, "min": 0.0011141735972950099, "max": 0.016981143901440586, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20451534091262144, "min": 0.014484256764835128, "max": 0.2377360146201682, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.569290334078571e-06, "min": 7.569290334078571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001059700646771, "min": 0.0001059700646771, "max": 0.0036330253889915996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025230642857143, "min": 0.1025230642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353229, "min": 1.3886848, "max": 2.6110084000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026205412214285714, "min": 0.00026205412214285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00366875771, "min": 0.00366875771, "max": 0.12111973916, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01264817826449871, "min": 0.01264817826449871, "max": 0.5465950965881348, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17707449197769165, "min": 0.17707449197769165, "max": 3.8261656761169434, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 383.02564102564105, "min": 324.0659340659341, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29876.0, "min": 15984.0, "max": 33005.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5656794714622009, "min": -1.0000000521540642, "max": 1.6319670174475556, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 122.12299877405167, "min": -28.322001732885838, "max": 148.50899858772755, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5656794714622009, "min": -1.0000000521540642, "max": 1.6319670174475556, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 122.12299877405167, "min": -28.322001732885838, "max": 148.50899858772755, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05026566562278626, "min": 0.04426909563841511, "max": 10.49105979129672, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9207219185773283, "min": 3.9207219185773283, "max": 167.85695666074753, "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": "1719742684", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719744910" }, "total": 2226.379663939001, "count": 1, "self": 0.848578896001527, "children": { "run_training.setup": { "total": 0.05253346900008182, "count": 1, "self": 0.05253346900008182 }, "TrainerController.start_learning": { "total": 2225.4785515739995, "count": 1, "self": 1.3184406959844637, "children": { "TrainerController._reset_env": { "total": 2.4576229060003243, "count": 1, "self": 2.4576229060003243 }, "TrainerController.advance": { "total": 2221.5818873290145, "count": 63865, "self": 1.3760955712150462, "children": { "env_step": { "total": 1578.4086364178274, "count": 63865, "self": 1446.0713860370797, "children": { "SubprocessEnvManager._take_step": { "total": 131.5442363958573, "count": 63865, "self": 4.583290846821001, "children": { "TorchPolicy.evaluate": { "total": 126.9609455490363, "count": 62564, "self": 126.9609455490363 } } }, "workers": { "total": 0.7930139848904219, "count": 63865, "self": 0.0, "children": { "worker_root": { "total": 2220.1792534261585, "count": 63865, "is_parallel": true, "self": 894.364544693176, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021413410004242905, "count": 1, "is_parallel": true, "self": 0.000634246003755834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015070949966684566, "count": 8, "is_parallel": true, "self": 0.0015070949966684566 } } }, "UnityEnvironment.step": { "total": 0.07230310599970835, "count": 1, "is_parallel": true, "self": 0.000616320999142772, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000458636000075785, "count": 1, "is_parallel": true, "self": 0.000458636000075785 }, "communicator.exchange": { "total": 0.06975871000031475, "count": 1, "is_parallel": true, "self": 0.06975871000031475 }, "steps_from_proto": { "total": 0.0014694390001750435, "count": 1, "is_parallel": true, "self": 0.000300138000966399, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011693009992086445, "count": 8, "is_parallel": true, "self": 0.0011693009992086445 } } } } } } }, "UnityEnvironment.step": { "total": 1325.8147087329826, "count": 63864, "is_parallel": true, "self": 33.70914165596605, "children": { "UnityEnvironment._generate_step_input": { "total": 22.75627686795451, "count": 63864, "is_parallel": true, "self": 22.75627686795451 }, "communicator.exchange": { "total": 1172.4692242190895, "count": 63864, "is_parallel": true, "self": 1172.4692242190895 }, "steps_from_proto": { "total": 96.88006598997254, "count": 63864, "is_parallel": true, "self": 19.317813873937666, "children": { "_process_rank_one_or_two_observation": { "total": 77.56225211603487, "count": 510912, "is_parallel": true, "self": 77.56225211603487 } } } } } } } } } } }, "trainer_advance": { "total": 641.797155339972, "count": 63865, "self": 2.5684806950812344, "children": { "process_trajectory": { "total": 127.1017614658931, "count": 63865, "self": 126.8772784618941, "children": { "RLTrainer._checkpoint": { "total": 0.224483003999012, "count": 2, "self": 0.224483003999012 } } }, "_update_policy": { "total": 512.1269131789977, "count": 453, "self": 304.8613184088772, "children": { "TorchPPOOptimizer.update": { "total": 207.26559477012052, "count": 22809, "self": 207.26559477012052 } } } } } } }, "trainer_threads": { "total": 1.1330012057442218e-06, "count": 1, "self": 1.1330012057442218e-06 }, "TrainerController._save_models": { "total": 0.12059950999901048, "count": 1, "self": 0.0019264239981566789, "children": { "RLTrainer._checkpoint": { "total": 0.1186730860008538, "count": 1, "self": 0.1186730860008538 } } } } } } }