{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6347436904907227, "min": 0.5423294305801392, "max": 1.4927983283996582, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19214.9609375, "min": 16269.8837890625, "max": 45285.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29886.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29886.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0654204860329628, "min": -0.1357545554637909, "max": 0.0654204860329628, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 16.158859252929688, "min": -32.173828125, "max": 16.158859252929688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012580049224197865, "min": 0.008633352816104889, "max": 0.18707874417304993, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.107272148132324, "min": 2.0806379318237305, "max": 45.085975646972656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06881148074734018, "min": 0.06457844910057257, "max": 0.07544862621059345, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9633607304627626, "min": 0.5281403834741542, "max": 1.0347653099212466, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008443433395750972, "min": 0.00011770223737134257, "max": 0.008443433395750972, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11820806754051362, "min": 0.001647831323198796, "max": 0.11820806754051362, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6146760332357165e-06, "min": 7.6146760332357165e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010660546446530003, "min": 0.00010660546446530003, "max": 0.0035077892307369993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253819285714284, "min": 0.10253819285714284, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355346999999998, "min": 1.3886848, "max": 2.5692630000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002635654664285715, "min": 0.0002635654664285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003689916530000001, "min": 0.003689916530000001, "max": 0.1169493737, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012107749469578266, "min": 0.011528367176651955, "max": 0.3820785582065582, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16950848698616028, "min": 0.16139714419841766, "max": 2.6745498180389404, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 758.8108108108108, "min": 758.8108108108108, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28076.0, "min": 16813.0, "max": 32548.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.23456311245497904, "min": -0.9998194070593003, "max": 0.23456311245497904, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 8.913398273289204, "min": -30.99440161883831, "max": 8.913398273289204, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.23456311245497904, "min": -0.9998194070593003, "max": 0.23456311245497904, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 8.913398273289204, "min": -30.99440161883831, "max": 8.913398273289204, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09513121292509727, "min": 0.09374604784210937, "max": 7.4121148472323135, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.614986091153696, "min": 3.3748577223159373, "max": 126.00595240294933, "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": "1710407214", "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=Pyramids1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710409188" }, "total": 1974.1803068320003, "count": 1, "self": 0.4970909490000395, "children": { "run_training.setup": { "total": 0.053993102000049475, "count": 1, "self": 0.053993102000049475 }, "TrainerController.start_learning": { "total": 1973.6292227810002, "count": 1, "self": 1.2755292719868976, "children": { "TrainerController._reset_env": { "total": 2.9461908749999566, "count": 1, "self": 2.9461908749999566 }, "TrainerController.advance": { "total": 1969.325824442013, "count": 63235, "self": 1.3132042350835036, "children": { "env_step": { "total": 1347.7809989029788, "count": 63235, "self": 1222.846778713916, "children": { "SubprocessEnvManager._take_step": { "total": 124.1465332810169, "count": 63235, "self": 4.472658276957645, "children": { "TorchPolicy.evaluate": { "total": 119.67387500405925, "count": 62561, "self": 119.67387500405925 } } }, "workers": { "total": 0.7876869080459983, "count": 63235, "self": 0.0, "children": { "worker_root": { "total": 1968.8678912570153, "count": 63235, "is_parallel": true, "self": 860.3710493230049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007765405000100145, "count": 1, "is_parallel": true, "self": 0.0036482940001860698, "children": { "_process_rank_one_or_two_observation": { "total": 0.004117110999914075, "count": 8, "is_parallel": true, "self": 0.004117110999914075 } } }, "UnityEnvironment.step": { "total": 0.05326883899988388, "count": 1, "is_parallel": true, "self": 0.0007327559997065691, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005400140000801912, "count": 1, "is_parallel": true, "self": 0.0005400140000801912 }, "communicator.exchange": { "total": 0.05010352900012549, "count": 1, "is_parallel": true, "self": 0.05010352900012549 }, "steps_from_proto": { "total": 0.001892539999971632, "count": 1, "is_parallel": true, "self": 0.0003840469998976914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015084930000739405, "count": 8, "is_parallel": true, "self": 0.0015084930000739405 } } } } } } }, "UnityEnvironment.step": { "total": 1108.4968419340105, "count": 63234, "is_parallel": true, "self": 34.05273268208225, "children": { "UnityEnvironment._generate_step_input": { "total": 23.369580042981625, "count": 63234, "is_parallel": true, "self": 23.369580042981625 }, "communicator.exchange": { "total": 954.0826657899631, "count": 63234, "is_parallel": true, "self": 954.0826657899631 }, "steps_from_proto": { "total": 96.99186341898348, "count": 63234, "is_parallel": true, "self": 19.167962714905798, "children": { "_process_rank_one_or_two_observation": { "total": 77.82390070407769, "count": 505872, "is_parallel": true, "self": 77.82390070407769 } } } } } } } } } } }, "trainer_advance": { "total": 620.2316213039508, "count": 63235, "self": 2.4533818269464973, "children": { "process_trajectory": { "total": 123.77912553301212, "count": 63235, "self": 123.49964073501178, "children": { "RLTrainer._checkpoint": { "total": 0.27948479800033965, "count": 2, "self": 0.27948479800033965 } } }, "_update_policy": { "total": 493.99911394399214, "count": 449, "self": 290.6959428749785, "children": { "TorchPPOOptimizer.update": { "total": 203.30317106901362, "count": 22788, "self": 203.30317106901362 } } } } } } }, "trainer_threads": { "total": 9.720001798996236e-07, "count": 1, "self": 9.720001798996236e-07 }, "TrainerController._save_models": { "total": 0.08167722000007416, "count": 1, "self": 0.0016062800000327115, "children": { "RLTrainer._checkpoint": { "total": 0.08007094000004145, "count": 1, "self": 0.08007094000004145 } } } } } } }