{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4401095509529114, "min": 0.42719903588294983, "max": 1.384224772453308, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13175.119140625, "min": 12638.255859375, "max": 41991.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29959.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29959.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3571150004863739, "min": -0.09607616066932678, "max": 0.40010347962379456, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.70681762695312, "min": -22.866127014160156, "max": 106.82762908935547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027814822271466255, "min": -0.002628646558150649, "max": 0.3108713924884796, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.454372406005859, "min": -0.6939626932144165, "max": 73.98738861083984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06379121950955043, "min": 0.06379121950955043, "max": 0.07260322353880232, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8930770731337059, "min": 0.5761177049408275, "max": 1.0890483530820347, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017464480543692065, "min": 0.0013920487489709995, "max": 0.017464480543692065, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2445027276116889, "min": 0.016704584987651993, "max": 0.2445027276116889, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.436004664221429e-06, "min": 7.436004664221429e-06, "max": 0.00029501175166275, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010410406529910001, "min": 0.00010410406529910001, "max": 0.003492330135889999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024786357142857, "min": 0.1024786357142857, "max": 0.19833725, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347008999999997, "min": 1.4347008999999997, "max": 2.572383200000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002576157078571429, "min": 0.0002576157078571429, "max": 0.009833891275, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036066199100000004, "min": 0.0036066199100000004, "max": 0.11642458900000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011781989596784115, "min": 0.011781989596784115, "max": 0.4199594259262085, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16494785249233246, "min": 0.16494785249233246, "max": 3.359675407409668, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 434.71830985915494, "min": 431.64179104477614, "max": 980.1875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30865.0, "min": 16118.0, "max": 32598.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4306833122132554, "min": -0.8568424754070513, "max": 1.4306833122132554, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.00919847935438, "min": -28.275801688432693, "max": 103.00919847935438, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4306833122132554, "min": -0.8568424754070513, "max": 1.4306833122132554, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.00919847935438, "min": -28.275801688432693, "max": 103.00919847935438, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05294481567964087, "min": 0.05294481567964087, "max": 8.271439988823499, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8120267289341427, "min": 3.611602952965768, "max": 140.61447980999947, "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": "1691854164", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691856531" }, "total": 2367.140538169, "count": 1, "self": 1.092234687000655, "children": { "run_training.setup": { "total": 0.04754448099993169, "count": 1, "self": 0.04754448099993169 }, "TrainerController.start_learning": { "total": 2366.0007590009996, "count": 1, "self": 1.4693136379933094, "children": { "TrainerController._reset_env": { "total": 4.11726319599984, "count": 1, "self": 4.11726319599984 }, "TrainerController.advance": { "total": 2360.2564457400067, "count": 63620, "self": 1.4253876988746015, "children": { "env_step": { "total": 1663.3963650271248, "count": 63620, "self": 1546.4751360310606, "children": { "SubprocessEnvManager._take_step": { "total": 116.02991351905393, "count": 63620, "self": 4.973095398084752, "children": { "TorchPolicy.evaluate": { "total": 111.05681812096918, "count": 62559, "self": 111.05681812096918 } } }, "workers": { "total": 0.8913154770102665, "count": 63620, "self": 0.0, "children": { "worker_root": { "total": 2360.4790948329883, "count": 63620, "is_parallel": true, "self": 934.3837678999507, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016927819997363258, "count": 1, "is_parallel": true, "self": 0.0005164719996173517, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011763100001189741, "count": 8, "is_parallel": true, "self": 0.0011763100001189741 } } }, "UnityEnvironment.step": { "total": 0.0460419420001017, "count": 1, "is_parallel": true, "self": 0.0005636020005113096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047328299979199073, "count": 1, "is_parallel": true, "self": 0.00047328299979199073 }, "communicator.exchange": { "total": 0.04304329399974449, "count": 1, "is_parallel": true, "self": 0.04304329399974449 }, "steps_from_proto": { "total": 0.0019617630000539066, "count": 1, "is_parallel": true, "self": 0.00042235900082232547, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015394039992315811, "count": 8, "is_parallel": true, "self": 0.0015394039992315811 } } } } } } }, "UnityEnvironment.step": { "total": 1426.0953269330375, "count": 63619, "is_parallel": true, "self": 35.49173163098885, "children": { "UnityEnvironment._generate_step_input": { "total": 23.405742976981855, "count": 63619, "is_parallel": true, "self": 23.405742976981855 }, "communicator.exchange": { "total": 1257.3534896480783, "count": 63619, "is_parallel": true, "self": 1257.3534896480783 }, "steps_from_proto": { "total": 109.84436267698857, "count": 63619, "is_parallel": true, "self": 21.705387305205022, "children": { "_process_rank_one_or_two_observation": { "total": 88.13897537178354, "count": 508952, "is_parallel": true, "self": 88.13897537178354 } } } } } } } } } } }, "trainer_advance": { "total": 695.4346930140073, "count": 63620, "self": 2.904138178959329, "children": { "process_trajectory": { "total": 116.04861135804458, "count": 63620, "self": 115.79287874304464, "children": { "RLTrainer._checkpoint": { "total": 0.2557326149999426, "count": 2, "self": 0.2557326149999426 } } }, "_update_policy": { "total": 576.4819434770034, "count": 457, "self": 373.6968971189767, "children": { "TorchPPOOptimizer.update": { "total": 202.78504635802665, "count": 22761, "self": 202.78504635802665 } } } } } } }, "trainer_threads": { "total": 1.3489998309523799e-06, "count": 1, "self": 1.3489998309523799e-06 }, "TrainerController._save_models": { "total": 0.15773507799985964, "count": 1, "self": 0.0018806959997164086, "children": { "RLTrainer._checkpoint": { "total": 0.15585438200014323, "count": 1, "self": 0.15585438200014323 } } } } } } }