{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5188910365104675, "min": 0.5177847743034363, "max": 1.397757649421692, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15541.82421875, "min": 15516.9736328125, "max": 42402.375, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45750558376312256, "min": -0.0848151370882988, "max": 0.4844558835029602, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.61149597167969, "min": -20.440448760986328, "max": 130.31863403320312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.029161421582102776, "min": -0.029161421582102776, "max": 0.39571771025657654, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.815260887145996, "min": -7.815260887145996, "max": 93.78509521484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06792384513065651, "min": 0.06490958266658707, "max": 0.0734338414211593, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0188576769598476, "min": 0.48358025351283673, "max": 1.044565084176914, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013090611569502761, "min": 0.0012658782114416747, "max": 0.01433566063062871, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19635917354254143, "min": 0.008861147480091723, "max": 0.20069924882880194, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.571437476220002e-06, "min": 7.571437476220002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011357156214330002, "min": 0.00011357156214330002, "max": 0.0037592242469252995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252378000000002, "min": 0.10252378000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378567000000003, "min": 1.3691136000000002, "max": 2.6530747, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000262125622, "min": 0.000262125622, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00393188433, "min": 0.00393188433, "max": 0.12532216252999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009280054830014706, "min": 0.009280054830014706, "max": 0.4777162969112396, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.139200821518898, "min": 0.13153129816055298, "max": 3.3440141677856445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 419.57142857142856, "min": 383.35135135135135, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29370.0, "min": 15984.0, "max": 33449.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.437545693559306, "min": -1.0000000521540642, "max": 1.51210956234638, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 100.62819854915142, "min": -32.000001668930054, "max": 111.62999815493822, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.437545693559306, "min": -1.0000000521540642, "max": 1.51210956234638, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 100.62819854915142, "min": -32.000001668930054, "max": 111.62999815493822, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039889879483546664, "min": 0.039889879483546664, "max": 9.342226451262832, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7922915638482664, "min": 2.7922915638482664, "max": 149.4756232202053, "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": "1712424698", "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 Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712427072" }, "total": 2374.1065205319996, "count": 1, "self": 0.8988956339994729, "children": { "run_training.setup": { "total": 0.05122429600010037, "count": 1, "self": 0.05122429600010037 }, "TrainerController.start_learning": { "total": 2373.156400602, "count": 1, "self": 1.8948408220157944, "children": { "TrainerController._reset_env": { "total": 2.12626107899996, "count": 1, "self": 2.12626107899996 }, "TrainerController.advance": { "total": 2368.9788220879836, "count": 63800, "self": 1.9723670110611238, "children": { "env_step": { "total": 1718.5323056149036, "count": 63800, "self": 1554.2027717299395, "children": { "SubprocessEnvManager._take_step": { "total": 163.11332203897496, "count": 63800, "self": 6.11540640999533, "children": { "TorchPolicy.evaluate": { "total": 156.99791562897963, "count": 62569, "self": 156.99791562897963 } } }, "workers": { "total": 1.2162118459891644, "count": 63800, "self": 0.0, "children": { "worker_root": { "total": 2366.7908769890164, "count": 63800, "is_parallel": true, "self": 962.5893403780196, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021733149999363377, "count": 1, "is_parallel": true, "self": 0.0006604779998724553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015128370000638824, "count": 8, "is_parallel": true, "self": 0.0015128370000638824 } } }, "UnityEnvironment.step": { "total": 0.05200437600001351, "count": 1, "is_parallel": true, "self": 0.0006921819999661238, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004368110000996239, "count": 1, "is_parallel": true, "self": 0.0004368110000996239 }, "communicator.exchange": { "total": 0.049203923000050054, "count": 1, "is_parallel": true, "self": 0.049203923000050054 }, "steps_from_proto": { "total": 0.0016714599998977064, "count": 1, "is_parallel": true, "self": 0.0003625279998686892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013089320000290172, "count": 8, "is_parallel": true, "self": 0.0013089320000290172 } } } } } } }, "UnityEnvironment.step": { "total": 1404.2015366109968, "count": 63799, "is_parallel": true, "self": 40.03658548795215, "children": { "UnityEnvironment._generate_step_input": { "total": 25.603799241987417, "count": 63799, "is_parallel": true, "self": 25.603799241987417 }, "communicator.exchange": { "total": 1226.304475118033, "count": 63799, "is_parallel": true, "self": 1226.304475118033 }, "steps_from_proto": { "total": 112.25667676302419, "count": 63799, "is_parallel": true, "self": 24.2227383300567, "children": { "_process_rank_one_or_two_observation": { "total": 88.03393843296749, "count": 510392, "is_parallel": true, "self": 88.03393843296749 } } } } } } } } } } }, "trainer_advance": { "total": 648.4741494620189, "count": 63800, "self": 3.5333817869613995, "children": { "process_trajectory": { "total": 135.71939528406006, "count": 63800, "self": 135.47919080605948, "children": { "RLTrainer._checkpoint": { "total": 0.2402044780005781, "count": 2, "self": 0.2402044780005781 } } }, "_update_policy": { "total": 509.22137239099743, "count": 454, "self": 296.9567129909599, "children": { "TorchPPOOptimizer.update": { "total": 212.26465940003754, "count": 22758, "self": 212.26465940003754 } } } } } } }, "trainer_threads": { "total": 2.083999788737856e-06, "count": 1, "self": 2.083999788737856e-06 }, "TrainerController._save_models": { "total": 0.15647452900066128, "count": 1, "self": 0.0025207230009982595, "children": { "RLTrainer._checkpoint": { "total": 0.15395380599966302, "count": 1, "self": 0.15395380599966302 } } } } } } }