{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37305524945259094, "min": 0.37305524945259094, "max": 1.5489435195922852, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11317.00390625, "min": 11317.00390625, "max": 46988.75, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5687825083732605, "min": -0.25425416231155396, "max": 0.6240326166152954, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.55274963378906, "min": -60.258235931396484, "max": 175.97720336914062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007374450098723173, "min": -0.06463734805583954, "max": 0.20690801739692688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.042722702026367, "min": -16.741073608398438, "max": 49.86483383178711, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06977546833583066, "min": 0.0633343095375624, "max": 0.07390616189583114, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9768565567016292, "min": 0.4902912792257949, "max": 1.0815248631988652, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015160610663033803, "min": 0.0011020373078210852, "max": 0.015160610663033803, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21224854928247325, "min": 0.01359967492163689, "max": 0.21224854928247325, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.61101174874286e-06, "min": 7.61101174874286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010655416448240004, "min": 0.00010655416448240004, "max": 0.0035078204307265994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253697142857143, "min": 0.10253697142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355176, "min": 1.3886848, "max": 2.6175899000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002634434457142858, "min": 0.0002634434457142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036882082400000018, "min": 0.0036882082400000018, "max": 0.11695041266000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008062896318733692, "min": 0.0080373864620924, "max": 0.3131609857082367, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11288054287433624, "min": 0.1125234067440033, "max": 2.192126989364624, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.2631578947368, "min": 326.20652173913044, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31375.0, "min": 15984.0, "max": 34700.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6257808347173193, "min": -1.0000000521540642, "max": 1.6703695450787959, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 152.82339846342802, "min": -28.937001734972, "max": 153.67399814724922, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6257808347173193, "min": -1.0000000521540642, "max": 1.6703695450787959, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 152.82339846342802, "min": -28.937001734972, "max": 153.67399814724922, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027549504300584383, "min": 0.027549504300584383, "max": 5.990333755500615, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.589653404254932, "min": 2.3761983209988102, "max": 95.84534008800983, "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": "1688361345", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1688363512" }, "total": 2166.606332537, "count": 1, "self": 0.47462073099995905, "children": { "run_training.setup": { "total": 0.038272824000159744, "count": 1, "self": 0.038272824000159744 }, "TrainerController.start_learning": { "total": 2166.093438982, "count": 1, "self": 1.2669112710213994, "children": { "TrainerController._reset_env": { "total": 4.275054532000013, "count": 1, "self": 4.275054532000013 }, "TrainerController.advance": { "total": 2160.4508361169787, "count": 64128, "self": 1.2628299109496766, "children": { "env_step": { "total": 1547.456354456043, "count": 64128, "self": 1442.5580124451587, "children": { "SubprocessEnvManager._take_step": { "total": 104.16146118692996, "count": 64128, "self": 4.479133668941358, "children": { "TorchPolicy.evaluate": { "total": 99.6823275179886, "count": 62566, "self": 99.6823275179886 } } }, "workers": { "total": 0.7368808239543796, "count": 64128, "self": 0.0, "children": { "worker_root": { "total": 2161.540317221974, "count": 64128, "is_parallel": true, "self": 825.0584730829705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019061569998939376, "count": 1, "is_parallel": true, "self": 0.0005582949995641684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013478620003297692, "count": 8, "is_parallel": true, "self": 0.0013478620003297692 } } }, "UnityEnvironment.step": { "total": 0.08825939000007565, "count": 1, "is_parallel": true, "self": 0.0005601300001671916, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004624030000286439, "count": 1, "is_parallel": true, "self": 0.0004624030000286439 }, "communicator.exchange": { "total": 0.08548500999995667, "count": 1, "is_parallel": true, "self": 0.08548500999995667 }, "steps_from_proto": { "total": 0.0017518469999231456, "count": 1, "is_parallel": true, "self": 0.00034567200009405497, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014061749998290907, "count": 8, "is_parallel": true, "self": 0.0014061749998290907 } } } } } } }, "UnityEnvironment.step": { "total": 1336.4818441390034, "count": 64127, "is_parallel": true, "self": 32.06007387007776, "children": { "UnityEnvironment._generate_step_input": { "total": 21.923908174949247, "count": 64127, "is_parallel": true, "self": 21.923908174949247 }, "communicator.exchange": { "total": 1184.9648444419197, "count": 64127, "is_parallel": true, "self": 1184.9648444419197 }, "steps_from_proto": { "total": 97.53301765205674, "count": 64127, "is_parallel": true, "self": 18.637282830100048, "children": { "_process_rank_one_or_two_observation": { "total": 78.8957348219567, "count": 513016, "is_parallel": true, "self": 78.8957348219567 } } } } } } } } } } }, "trainer_advance": { "total": 611.7316517499862, "count": 64128, "self": 2.466526309999608, "children": { "process_trajectory": { "total": 106.12636464798584, "count": 64128, "self": 105.8734203219858, "children": { "RLTrainer._checkpoint": { "total": 0.25294432600003347, "count": 2, "self": 0.25294432600003347 } } }, "_update_policy": { "total": 503.13876079200077, "count": 453, "self": 317.9802672890178, "children": { "TorchPPOOptimizer.update": { "total": 185.158493502983, "count": 22782, "self": 185.158493502983 } } } } } } }, "trainer_threads": { "total": 1.0680000741558615e-06, "count": 1, "self": 1.0680000741558615e-06 }, "TrainerController._save_models": { "total": 0.100635993999731, "count": 1, "self": 0.00140892299987172, "children": { "RLTrainer._checkpoint": { "total": 0.09922707099985928, "count": 1, "self": 0.09922707099985928 } } } } } } }