{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3370457589626312, "min": 0.3370457589626312, "max": 1.4654326438903809, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10003.5185546875, "min": 10003.5185546875, "max": 44455.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29952.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6257880330085754, "min": -0.15205053985118866, "max": 0.6948519945144653, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 173.9690704345703, "min": -36.492130279541016, "max": 202.89678955078125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03587191924452782, "min": -0.004720490425825119, "max": 0.22085019946098328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.972393989562988, "min": -1.1848430633544922, "max": 53.00404739379883, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06973792193457486, "min": 0.06506195106941108, "max": 0.07226451763052938, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9763309070840479, "min": 0.4897804074531324, "max": 1.0623100782383927, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013992820218845736, "min": 0.00032896048798924005, "max": 0.018658826554504532, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1958994830638403, "min": 0.00411319138033414, "max": 0.26122357176306343, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.325647558149996e-06, "min": 7.325647558149996e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010255906581409994, "min": 0.00010255906581409994, "max": 0.0032587328137557996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244185000000001, "min": 0.10244185000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341859000000001, "min": 1.3691136000000002, "max": 2.5274384000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002539408149999999, "min": 0.0002539408149999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035551714099999986, "min": 0.0035551714099999986, "max": 0.10864579557999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009647871367633343, "min": 0.009647871367633343, "max": 0.32972434163093567, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13507020473480225, "min": 0.13507020473480225, "max": 2.308070421218872, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.8041237113402, "min": 272.87068965517244, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28402.0, "min": 15984.0, "max": 34125.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6866645684155326, "min": -1.0000000521540642, "max": 1.7098810162780613, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 161.91979856789112, "min": -32.000001668930054, "max": 198.34619788825512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6866645684155326, "min": -1.0000000521540642, "max": 1.7098810162780613, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 161.91979856789112, "min": -32.000001668930054, "max": 198.34619788825512, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02950822603687205, "min": 0.029139482520616277, "max": 7.001645186915994, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.832789699539717, "min": 2.832789699539717, "max": 112.0263229906559, "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": "1693161540", "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": "1693163820" }, "total": 2279.536728576, "count": 1, "self": 0.44628317900014736, "children": { "run_training.setup": { "total": 0.04082327400010399, "count": 1, "self": 0.04082327400010399 }, "TrainerController.start_learning": { "total": 2279.0496221229996, "count": 1, "self": 1.5049627829912424, "children": { "TrainerController._reset_env": { "total": 4.0934438030001274, "count": 1, "self": 4.0934438030001274 }, "TrainerController.advance": { "total": 2273.354632718009, "count": 63981, "self": 1.5776902311145022, "children": { "env_step": { "total": 1609.861247671918, "count": 63981, "self": 1497.2958793908524, "children": { "SubprocessEnvManager._take_step": { "total": 111.67411854102329, "count": 63981, "self": 4.857536704010272, "children": { "TorchPolicy.evaluate": { "total": 106.81658183701302, "count": 62572, "self": 106.81658183701302 } } }, "workers": { "total": 0.8912497400422126, "count": 63981, "self": 0.0, "children": { "worker_root": { "total": 2273.9870388279683, "count": 63981, "is_parallel": true, "self": 893.9694771029303, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018098569998983294, "count": 1, "is_parallel": true, "self": 0.0005686029999196762, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012412539999786532, "count": 8, "is_parallel": true, "self": 0.0012412539999786532 } } }, "UnityEnvironment.step": { "total": 0.04632939999987684, "count": 1, "is_parallel": true, "self": 0.0005560109996167739, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004841690001740062, "count": 1, "is_parallel": true, "self": 0.0004841690001740062 }, "communicator.exchange": { "total": 0.0433882550000817, "count": 1, "is_parallel": true, "self": 0.0433882550000817 }, "steps_from_proto": { "total": 0.001900965000004362, "count": 1, "is_parallel": true, "self": 0.00036487800025497563, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015360869997493865, "count": 8, "is_parallel": true, "self": 0.0015360869997493865 } } } } } } }, "UnityEnvironment.step": { "total": 1380.017561725038, "count": 63980, "is_parallel": true, "self": 34.68697189003001, "children": { "UnityEnvironment._generate_step_input": { "total": 23.220177958930662, "count": 63980, "is_parallel": true, "self": 23.220177958930662 }, "communicator.exchange": { "total": 1215.0257351510402, "count": 63980, "is_parallel": true, "self": 1215.0257351510402 }, "steps_from_proto": { "total": 107.08467672503707, "count": 63980, "is_parallel": true, "self": 21.045894979907416, "children": { "_process_rank_one_or_two_observation": { "total": 86.03878174512965, "count": 511840, "is_parallel": true, "self": 86.03878174512965 } } } } } } } } } } }, "trainer_advance": { "total": 661.9156948149764, "count": 63981, "self": 2.7661197349470967, "children": { "process_trajectory": { "total": 109.81843083703234, "count": 63981, "self": 109.60940987303229, "children": { "RLTrainer._checkpoint": { "total": 0.20902096400004666, "count": 2, "self": 0.20902096400004666 } } }, "_update_policy": { "total": 549.331144242997, "count": 441, "self": 359.74074917498774, "children": { "TorchPPOOptimizer.update": { "total": 189.59039506800923, "count": 22887, "self": 189.59039506800923 } } } } } } }, "trainer_threads": { "total": 1.0049998309114017e-06, "count": 1, "self": 1.0049998309114017e-06 }, "TrainerController._save_models": { "total": 0.09658181399936439, "count": 1, "self": 0.0015746109993415303, "children": { "RLTrainer._checkpoint": { "total": 0.09500720300002286, "count": 1, "self": 0.09500720300002286 } } } } } } }