{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8658556342124939, "min": 0.8568869233131409, "max": 1.3608918190002441, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 26169.62109375, "min": 25473.53515625, "max": 41284.015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03867529332637787, "min": -0.11774829030036926, "max": 0.08777497708797455, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 9.475446701049805, "min": -28.495086669921875, "max": 20.802669525146484, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.021831199526786804, "min": -0.036457180976867676, "max": 0.44904839992523193, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.348643779754639, "min": -9.004923820495605, "max": 106.42446899414062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0665718631436383, "min": 0.06585706145270612, "max": 0.07380919246817776, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9320060840109363, "min": 0.5038065833988634, "max": 1.0333286945544886, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005783018441253371, "min": 8.590104548686253e-05, "max": 0.005783018441253371, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0809622581775472, "min": 0.0011167135913292129, "max": 0.0809622581775472, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.633918883964288e-06, "min": 7.633918883964288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010687486437550002, "min": 0.00010687486437550002, "max": 0.0031440710519763998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254460714285717, "min": 0.10254460714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356245000000003, "min": 1.3691136000000002, "max": 2.3480236000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002642062535714286, "min": 0.0002642062535714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003698887550000001, "min": 0.003698887550000001, "max": 0.10482755764, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008972590789198875, "min": 0.00880782026797533, "max": 0.38569894433021545, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12561626732349396, "min": 0.12330947816371918, "max": 2.699892520904541, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 842.1351351351351, "min": 832.7567567567568, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31159.0, "min": 15984.0, "max": 32651.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.13980003828937942, "min": -1.0000000521540642, "max": 0.049949954781267375, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -5.172601416707039, "min": -32.000001668930054, "max": 1.7981983721256256, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.13980003828937942, "min": -1.0000000521540642, "max": 0.049949954781267375, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -5.172601416707039, "min": -32.000001668930054, "max": 1.7981983721256256, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07859579662200869, "min": 0.07859579662200869, "max": 7.631403457373381, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9080444750143215, "min": 2.711899575719144, "max": 122.10245531797409, "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": "1711927043", "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=Pyramids Training --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": "1711928708" }, "total": 1664.5762981699997, "count": 1, "self": 0.32260139199979676, "children": { "run_training.setup": { "total": 0.05536682199999632, "count": 1, "self": 0.05536682199999632 }, "TrainerController.start_learning": { "total": 1664.198329956, "count": 1, "self": 1.5714458640072735, "children": { "TrainerController._reset_env": { "total": 2.958404883999947, "count": 1, "self": 2.958404883999947 }, "TrainerController.advance": { "total": 1659.5869754989926, "count": 63010, "self": 1.5951992899620109, "children": { "env_step": { "total": 1063.315044602011, "count": 63010, "self": 922.0231450651331, "children": { "SubprocessEnvManager._take_step": { "total": 140.31523106992654, "count": 63010, "self": 4.801478914909012, "children": { "TorchPolicy.evaluate": { "total": 135.51375215501753, "count": 62559, "self": 135.51375215501753 } } }, "workers": { "total": 0.9766684669514234, "count": 63010, "self": 0.0, "children": { "worker_root": { "total": 1661.4855698470174, "count": 63010, "is_parallel": true, "self": 848.8472684300114, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021712180000577064, "count": 1, "is_parallel": true, "self": 0.0006778430001759261, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014933749998817802, "count": 8, "is_parallel": true, "self": 0.0014933749998817802 } } }, "UnityEnvironment.step": { "total": 0.03606010100020285, "count": 1, "is_parallel": true, "self": 0.0004457350000848237, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003705759997956193, "count": 1, "is_parallel": true, "self": 0.0003705759997956193 }, "communicator.exchange": { "total": 0.034031902000151604, "count": 1, "is_parallel": true, "self": 0.034031902000151604 }, "steps_from_proto": { "total": 0.0012118880001708021, "count": 1, "is_parallel": true, "self": 0.0002852079999229318, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009266800002478703, "count": 8, "is_parallel": true, "self": 0.0009266800002478703 } } } } } } }, "UnityEnvironment.step": { "total": 812.638301417006, "count": 63009, "is_parallel": true, "self": 24.96046847192065, "children": { "UnityEnvironment._generate_step_input": { "total": 15.038778053086617, "count": 63009, "is_parallel": true, "self": 15.038778053086617 }, "communicator.exchange": { "total": 705.7792937270658, "count": 63009, "is_parallel": true, "self": 705.7792937270658 }, "steps_from_proto": { "total": 66.85976116493293, "count": 63009, "is_parallel": true, "self": 14.941342634938337, "children": { "_process_rank_one_or_two_observation": { "total": 51.9184185299946, "count": 504072, "is_parallel": true, "self": 51.9184185299946 } } } } } } } } } } }, "trainer_advance": { "total": 594.6767316070195, "count": 63010, "self": 2.846937189087839, "children": { "process_trajectory": { "total": 117.57600385193018, "count": 63010, "self": 117.31392448593033, "children": { "RLTrainer._checkpoint": { "total": 0.2620793659998526, "count": 2, "self": 0.2620793659998526 } } }, "_update_policy": { "total": 474.2537905660015, "count": 431, "self": 274.0311528389941, "children": { "TorchPPOOptimizer.update": { "total": 200.2226377270074, "count": 22842, "self": 200.2226377270074 } } } } } } }, "trainer_threads": { "total": 1.030000021273736e-06, "count": 1, "self": 1.030000021273736e-06 }, "TrainerController._save_models": { "total": 0.08150267900009567, "count": 1, "self": 0.0013431419997687044, "children": { "RLTrainer._checkpoint": { "total": 0.08015953700032696, "count": 1, "self": 0.08015953700032696 } } } } } } }