{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4842098653316498, "min": 0.4842098653316498, "max": 1.4386916160583496, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14425.580078125, "min": 14425.580078125, "max": 43644.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989905.0, "min": 29952.0, "max": 989905.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.37882742285728455, "min": -0.1089899018406868, "max": 0.37882742285728455, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.90457916259766, "min": -26.26656723022461, "max": 101.90457916259766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026161467656493187, "min": 0.0024595577269792557, "max": 0.2871797978878021, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.0374345779418945, "min": 0.6394850015640259, "max": 68.06161499023438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06969184971280645, "min": 0.06388195068506147, "max": 0.07426018445920718, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9756858959792903, "min": 0.5051695327766256, "max": 1.1139027668881076, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012839457883933838, "min": 0.0003373815997836606, "max": 0.012839457883933838, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17975241037507372, "min": 0.004385960797187588, "max": 0.17975241037507372, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.490604646021427e-06, "min": 7.490604646021427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010486846504429997, "min": 0.00010486846504429997, "max": 0.0033819740726754003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249683571428572, "min": 0.10249683571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349557000000002, "min": 1.3886848, "max": 2.5273246000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025943388785714284, "min": 0.00025943388785714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036320744299999995, "min": 0.0036320744299999995, "max": 0.11275972754, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011045611463487148, "min": 0.011045611463487148, "max": 0.4658391773700714, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15463855862617493, "min": 0.15463855862617493, "max": 3.2608742713928223, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 456.875, "min": 456.875, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29240.0, "min": 15984.0, "max": 32649.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3555562307592481, "min": -1.0000000521540642, "max": 1.3555562307592481, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.75559876859188, "min": -30.68100170791149, "max": 86.75559876859188, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3555562307592481, "min": -1.0000000521540642, "max": 1.3555562307592481, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.75559876859188, "min": -30.68100170791149, "max": 86.75559876859188, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05220603553198089, "min": 0.05220603553198089, "max": 9.173284641467035, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.341186274046777, "min": 3.341186274046777, "max": 146.77255426347256, "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": "1701816543", "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=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701819637" }, "total": 3094.565600102, "count": 1, "self": 0.5924958289997448, "children": { "run_training.setup": { "total": 0.06320639100010794, "count": 1, "self": 0.06320639100010794 }, "TrainerController.start_learning": { "total": 3093.909897882, "count": 1, "self": 2.2143090230315465, "children": { "TrainerController._reset_env": { "total": 2.4708830450000505, "count": 1, "self": 2.4708830450000505 }, "TrainerController.advance": { "total": 3089.1432898509684, "count": 63447, "self": 2.561102687966013, "children": { "env_step": { "total": 2031.9909404450293, "count": 63447, "self": 1873.6765204840856, "children": { "SubprocessEnvManager._take_step": { "total": 156.87333825398355, "count": 63447, "self": 7.023144813997419, "children": { "TorchPolicy.evaluate": { "total": 149.85019343998613, "count": 62566, "self": 149.85019343998613 } } }, "workers": { "total": 1.4410817069601762, "count": 63447, "self": 0.0, "children": { "worker_root": { "total": 3087.963895852038, "count": 63447, "is_parallel": true, "self": 1386.951169150134, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025207510000200273, "count": 1, "is_parallel": true, "self": 0.0008839239999360871, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016368270000839402, "count": 8, "is_parallel": true, "self": 0.0016368270000839402 } } }, "UnityEnvironment.step": { "total": 0.06378786400000536, "count": 1, "is_parallel": true, "self": 0.0006733209999083556, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005597540000508161, "count": 1, "is_parallel": true, "self": 0.0005597540000508161 }, "communicator.exchange": { "total": 0.060537713000030635, "count": 1, "is_parallel": true, "self": 0.060537713000030635 }, "steps_from_proto": { "total": 0.0020170760000155497, "count": 1, "is_parallel": true, "self": 0.0004416780001292864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015753979998862633, "count": 8, "is_parallel": true, "self": 0.0015753979998862633 } } } } } } }, "UnityEnvironment.step": { "total": 1701.012726701904, "count": 63446, "is_parallel": true, "self": 45.47920844590635, "children": { "UnityEnvironment._generate_step_input": { "total": 27.340589469985957, "count": 63446, "is_parallel": true, "self": 27.340589469985957 }, "communicator.exchange": { "total": 1500.4888696280616, "count": 63446, "is_parallel": true, "self": 1500.4888696280616 }, "steps_from_proto": { "total": 127.70405915795004, "count": 63446, "is_parallel": true, "self": 27.238469746912187, "children": { "_process_rank_one_or_two_observation": { "total": 100.46558941103785, "count": 507568, "is_parallel": true, "self": 100.46558941103785 } } } } } } } } } } }, "trainer_advance": { "total": 1054.5912467179728, "count": 63447, "self": 4.5006613360155825, "children": { "process_trajectory": { "total": 162.56362080595716, "count": 63447, "self": 162.3524976349571, "children": { "RLTrainer._checkpoint": { "total": 0.21112317100005384, "count": 2, "self": 0.21112317100005384 } } }, "_update_policy": { "total": 887.526964576, "count": 449, "self": 369.86699784798, "children": { "TorchPPOOptimizer.update": { "total": 517.65996672802, "count": 22797, "self": 517.65996672802 } } } } } } }, "trainer_threads": { "total": 1.1730003279808443e-06, "count": 1, "self": 1.1730003279808443e-06 }, "TrainerController._save_models": { "total": 0.08141479000005347, "count": 1, "self": 0.0018592180003906833, "children": { "RLTrainer._checkpoint": { "total": 0.07955557199966279, "count": 1, "self": 0.07955557199966279 } } } } } } }