{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33739957213401794, "min": 0.33635392785072327, "max": 1.420432209968567, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9992.42578125, "min": 9992.42578125, "max": 43090.23046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4746622145175934, "min": -0.08456341922283173, "max": 0.529676079750061, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.0574493408203, "min": -20.379783630371094, "max": 145.13124084472656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028834905475378036, "min": -0.0017789301928132772, "max": 0.5447912812232971, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.900763988494873, "min": -0.4589639902114868, "max": 129.11553955078125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06677943454112621, "min": 0.06564740413506072, "max": 0.07429961927991012, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9349120835757669, "min": 0.5164281227818259, "max": 1.082917795250764, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01732950886951646, "min": 0.0014993300557136406, "max": 0.01732950886951646, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24261312417323044, "min": 0.01996087022779049, "max": 0.24261312417323044, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.598711752842855e-06, "min": 7.598711752842855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010638196453979997, "min": 0.00010638196453979997, "max": 0.0035082209305931, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253287142857141, "min": 0.10253287142857141, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354601999999999, "min": 1.3886848, "max": 2.5726590999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630338557142857, "min": 0.0002630338557142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00368247398, "min": 0.00368247398, "max": 0.11696374931, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012795268557965755, "min": 0.012795268557965755, "max": 0.5148599147796631, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17913375794887543, "min": 0.17913375794887543, "max": 3.6040194034576416, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 378.5365853658537, "min": 358.21176470588233, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31040.0, "min": 15984.0, "max": 33106.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5456419531026004, "min": -1.0000000521540642, "max": 1.5823174781166016, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.19699820131063, "min": -29.138001799583435, "max": 133.54979837685823, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5456419531026004, "min": -1.0000000521540642, "max": 1.5823174781166016, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.19699820131063, "min": -29.138001799583435, "max": 133.54979837685823, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05055506053085318, "min": 0.04972209168918198, "max": 10.354995897039771, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.094959902999108, "min": 3.9777673351345584, "max": 165.67993435263634, "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": "1685669163", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685672758" }, "total": 3595.438370092, "count": 1, "self": 0.6272584449998249, "children": { "run_training.setup": { "total": 0.050962860000254295, "count": 1, "self": 0.050962860000254295 }, "TrainerController.start_learning": { "total": 3594.7601487869997, "count": 1, "self": 2.4162212431633634, "children": { "TrainerController._reset_env": { "total": 1.0940734209998482, "count": 1, "self": 1.0940734209998482 }, "TrainerController.advance": { "total": 3591.1394283368368, "count": 63831, "self": 2.5130407539249973, "children": { "env_step": { "total": 2349.3826012220434, "count": 63831, "self": 2205.6240973090307, "children": { "SubprocessEnvManager._take_step": { "total": 142.3062735009239, "count": 63831, "self": 7.223518056871399, "children": { "TorchPolicy.evaluate": { "total": 135.0827554440525, "count": 62571, "self": 135.0827554440525 } } }, "workers": { "total": 1.4522304120887384, "count": 63831, "self": 0.0, "children": { "worker_root": { "total": 3587.0207213558733, "count": 63831, "is_parallel": true, "self": 1559.9241987558612, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028728399997817178, "count": 1, "is_parallel": true, "self": 0.000980395999704342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018924440000773757, "count": 8, "is_parallel": true, "self": 0.0018924440000773757 } } }, "UnityEnvironment.step": { "total": 0.06960923099995853, "count": 1, "is_parallel": true, "self": 0.0007322580004256452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007528239998464414, "count": 1, "is_parallel": true, "self": 0.0007528239998464414 }, "communicator.exchange": { "total": 0.06584601299982751, "count": 1, "is_parallel": true, "self": 0.06584601299982751 }, "steps_from_proto": { "total": 0.0022781359998589323, "count": 1, "is_parallel": true, "self": 0.0004365709996818623, "children": { "_process_rank_one_or_two_observation": { "total": 0.00184156500017707, "count": 8, "is_parallel": true, "self": 0.00184156500017707 } } } } } } }, "UnityEnvironment.step": { "total": 2027.0965226000121, "count": 63830, "is_parallel": true, "self": 47.18188184293331, "children": { "UnityEnvironment._generate_step_input": { "total": 26.692858521016205, "count": 63830, "is_parallel": true, "self": 26.692858521016205 }, "communicator.exchange": { "total": 1808.6970074421024, "count": 63830, "is_parallel": true, "self": 1808.6970074421024 }, "steps_from_proto": { "total": 144.5247747939602, "count": 63830, "is_parallel": true, "self": 31.07001625391922, "children": { "_process_rank_one_or_two_observation": { "total": 113.45475854004098, "count": 510640, "is_parallel": true, "self": 113.45475854004098 } } } } } } } } } } }, "trainer_advance": { "total": 1239.2437863608684, "count": 63831, "self": 4.5291333318473335, "children": { "process_trajectory": { "total": 154.56293077602913, "count": 63831, "self": 154.33287402902988, "children": { "RLTrainer._checkpoint": { "total": 0.23005674699925294, "count": 2, "self": 0.23005674699925294 } } }, "_update_policy": { "total": 1080.151722252992, "count": 453, "self": 445.65416460994356, "children": { "TorchPPOOptimizer.update": { "total": 634.4975576430484, "count": 22800, "self": 634.4975576430484 } } } } } } }, "trainer_threads": { "total": 1.0459998520673253e-06, "count": 1, "self": 1.0459998520673253e-06 }, "TrainerController._save_models": { "total": 0.11042473999987124, "count": 1, "self": 0.0016680790004102164, "children": { "RLTrainer._checkpoint": { "total": 0.10875666099946102, "count": 1, "self": 0.10875666099946102 } } } } } } }