{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4642966687679291, "min": 0.4642966687679291, "max": 1.484009861946106, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13943.7578125, "min": 13943.7578125, "max": 45018.921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29898.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29898.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.021825531497597694, "min": -0.09786876291036606, "max": 0.09173505008220673, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 5.369080543518066, "min": -23.58637237548828, "max": 22.62625503540039, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.3118276000022888, "min": -0.43863627314567566, "max": 0.3407142162322998, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -76.70958709716797, "min": -108.78179931640625, "max": 80.749267578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06967869530473013, "min": 0.06509801640693934, "max": 0.0739830561770861, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.045180429570952, "min": 0.4945994608832494, "max": 1.045180429570952, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.067979579320287, "min": 0.0003506637609488277, "max": 0.08851575417997164, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.019693689804305, "min": 0.004909292653283588, "max": 1.239220558519603, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.530097490000003e-06, "min": 7.530097490000003e-06, "max": 0.0002952352301596857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011295146235000004, "min": 0.00011295146235000004, "max": 0.0033829793723402996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251000000000002, "min": 0.10251000000000002, "max": 0.19841174285714283, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376500000000002, "min": 1.3888821999999998, "max": 2.5276597000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607490000000001, "min": 0.0002607490000000001, "max": 0.00984133311142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003911235000000002, "min": 0.003911235000000002, "max": 0.11279320403, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009491994976997375, "min": 0.008725428022444248, "max": 0.3398001492023468, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14237992465496063, "min": 0.12215598672628403, "max": 2.37860107421875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 825.6857142857143, "min": 748.4102564102565, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28899.0, "min": 16569.0, "max": 32554.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.14031432356153214, "min": -1.0000000521540642, "max": 0.3282409902566519, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -4.9110013246536255, "min": -32.000001668930054, "max": 12.801398620009422, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.14031432356153214, "min": -1.0000000521540642, "max": 0.3282409902566519, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -4.9110013246536255, "min": -32.000001668930054, "max": 12.801398620009422, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08124714892557157, "min": 0.07665323025975267, "max": 6.185329051578746, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.843650212395005, "min": 2.8361695196108485, "max": 105.15059387683868, "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": "1694363475", "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": "1694365519" }, "total": 2044.0806629070003, "count": 1, "self": 0.4927108330005012, "children": { "run_training.setup": { "total": 0.04433304600001975, "count": 1, "self": 0.04433304600001975 }, "TrainerController.start_learning": { "total": 2043.5436190279997, "count": 1, "self": 1.3771754659851467, "children": { "TrainerController._reset_env": { "total": 4.156572452999853, "count": 1, "self": 4.156572452999853 }, "TrainerController.advance": { "total": 2037.915302879015, "count": 63180, "self": 1.3317532609969476, "children": { "env_step": { "total": 1379.314795601962, "count": 63180, "self": 1271.876302146006, "children": { "SubprocessEnvManager._take_step": { "total": 106.62875964598447, "count": 63180, "self": 4.687830542979555, "children": { "TorchPolicy.evaluate": { "total": 101.94092910300492, "count": 62557, "self": 101.94092910300492 } } }, "workers": { "total": 0.8097338099714761, "count": 63180, "self": 0.0, "children": { "worker_root": { "total": 2039.2797932900069, "count": 63180, "is_parallel": true, "self": 876.2746777990403, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017246040001737128, "count": 1, "is_parallel": true, "self": 0.0005186970001886948, "children": { "_process_rank_one_or_two_observation": { "total": 0.001205906999985018, "count": 8, "is_parallel": true, "self": 0.001205906999985018 } } }, "UnityEnvironment.step": { "total": 0.04870490199982669, "count": 1, "is_parallel": true, "self": 0.0005617659994641144, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005240820000835811, "count": 1, "is_parallel": true, "self": 0.0005240820000835811 }, "communicator.exchange": { "total": 0.04570557000010922, "count": 1, "is_parallel": true, "self": 0.04570557000010922 }, "steps_from_proto": { "total": 0.001913484000169774, "count": 1, "is_parallel": true, "self": 0.0003808619999290386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015326220002407354, "count": 8, "is_parallel": true, "self": 0.0015326220002407354 } } } } } } }, "UnityEnvironment.step": { "total": 1163.0051154909665, "count": 63179, "is_parallel": true, "self": 33.56994190689488, "children": { "UnityEnvironment._generate_step_input": { "total": 23.235461105013655, "count": 63179, "is_parallel": true, "self": 23.235461105013655 }, "communicator.exchange": { "total": 1002.60224397604, "count": 63179, "is_parallel": true, "self": 1002.60224397604 }, "steps_from_proto": { "total": 103.59746850301804, "count": 63179, "is_parallel": true, "self": 20.00788754392397, "children": { "_process_rank_one_or_two_observation": { "total": 83.58958095909406, "count": 505432, "is_parallel": true, "self": 83.58958095909406 } } } } } } } } } } }, "trainer_advance": { "total": 657.2687540160559, "count": 63180, "self": 2.4335144220012808, "children": { "process_trajectory": { "total": 108.73936469205478, "count": 63180, "self": 108.52997547605469, "children": { "RLTrainer._checkpoint": { "total": 0.20938921600009053, "count": 2, "self": 0.20938921600009053 } } }, "_update_policy": { "total": 546.0958749019999, "count": 442, "self": 355.6355490569813, "children": { "TorchPPOOptimizer.update": { "total": 190.4603258450186, "count": 22767, "self": 190.4603258450186 } } } } } } }, "trainer_threads": { "total": 1.0489998203411233e-06, "count": 1, "self": 1.0489998203411233e-06 }, "TrainerController._save_models": { "total": 0.09456718100000217, "count": 1, "self": 0.0015239540002767171, "children": { "RLTrainer._checkpoint": { "total": 0.09304322699972545, "count": 1, "self": 0.09304322699972545 } } } } } } }