{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4067658185958862, "min": 1.4067658185958862, "max": 1.427208662033081, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69141.1328125, "min": 69006.5078125, "max": 75796.53125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.630859375, "min": 88.45405405405405, "max": 398.0238095238095, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49475.0, "min": 48866.0, "max": 50153.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999970.0, "min": 49527.0, "max": 1999970.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999970.0, "min": 49527.0, "max": 1999970.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4213707447052, "min": 0.11924418061971664, "max": 2.448211669921875, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1239.7418212890625, "min": 14.905522346496582, "max": 1340.181884765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7267552100820467, "min": 1.9037067604064941, "max": 3.9679874828817314, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1908.098667562008, "min": 237.96334505081177, "max": 2141.177557885647, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7267552100820467, "min": 1.9037067604064941, "max": 3.9679874828817314, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1908.098667562008, "min": 237.96334505081177, "max": 2141.177557885647, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01804036701828914, "min": 0.014229931338437987, "max": 0.02201210239776022, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05412110105486742, "min": 0.028459862676875974, "max": 0.05412110105486742, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05372285611099667, "min": 0.02204858042920629, "max": 0.05731071395178636, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16116856833299, "min": 0.04409716085841258, "max": 0.16771064462761082, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.314798895099992e-06, "min": 3.314798895099992e-06, "max": 0.0002953417515527499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.944396685299976e-06, "min": 9.944396685299976e-06, "max": 0.0008440582686472497, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110490000000001, "min": 0.10110490000000001, "max": 0.19844725000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30331470000000005, "min": 0.20734005, "max": 0.58135275, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.513450999999989e-05, "min": 6.513450999999989e-05, "max": 0.0049225177749999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019540352999999967, "min": 0.00019540352999999967, "max": 0.014069502225000002, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701640866", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701643404" }, "total": 2538.236223074, "count": 1, "self": 0.44680232900009287, "children": { "run_training.setup": { "total": 0.056946673999959785, "count": 1, "self": 0.056946673999959785 }, "TrainerController.start_learning": { "total": 2537.732474071, "count": 1, "self": 4.644390280918287, "children": { "TrainerController._reset_env": { "total": 4.650174629999981, "count": 1, "self": 4.650174629999981 }, "TrainerController.advance": { "total": 2528.3319740010816, "count": 232013, "self": 4.822322036173773, "children": { "env_step": { "total": 1996.670278114002, "count": 232013, "self": 1648.375621654939, "children": { "SubprocessEnvManager._take_step": { "total": 345.2875874230155, "count": 232013, "self": 16.939328121078745, "children": { "TorchPolicy.evaluate": { "total": 328.34825930193676, "count": 222910, "self": 328.34825930193676 } } }, "workers": { "total": 3.0070690360474828, "count": 232013, "self": 0.0, "children": { "worker_root": { "total": 2530.1580343950513, "count": 232013, "is_parallel": true, "self": 1191.7252001311085, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009485070000323503, "count": 1, "is_parallel": true, "self": 0.0002744840000445947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006740229999877556, "count": 2, "is_parallel": true, "self": 0.0006740229999877556 } } }, "UnityEnvironment.step": { "total": 0.029782447999991746, "count": 1, "is_parallel": true, "self": 0.00034807399998726396, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019830200000114928, "count": 1, "is_parallel": true, "self": 0.00019830200000114928 }, "communicator.exchange": { "total": 0.028479150000009668, "count": 1, "is_parallel": true, "self": 0.028479150000009668 }, "steps_from_proto": { "total": 0.0007569219999936649, "count": 1, "is_parallel": true, "self": 0.00020619299999680152, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005507289999968634, "count": 2, "is_parallel": true, "self": 0.0005507289999968634 } } } } } } }, "UnityEnvironment.step": { "total": 1338.4328342639428, "count": 232012, "is_parallel": true, "self": 41.613664336047805, "children": { "UnityEnvironment._generate_step_input": { "total": 85.43905978896606, "count": 232012, "is_parallel": true, "self": 85.43905978896606 }, "communicator.exchange": { "total": 1117.599161402985, "count": 232012, "is_parallel": true, "self": 1117.599161402985 }, "steps_from_proto": { "total": 93.7809487359441, "count": 232012, "is_parallel": true, "self": 32.802709140017555, "children": { "_process_rank_one_or_two_observation": { "total": 60.97823959592654, "count": 464024, "is_parallel": true, "self": 60.97823959592654 } } } } } } } } } } }, "trainer_advance": { "total": 526.839373850906, "count": 232013, "self": 7.470373825909746, "children": { "process_trajectory": { "total": 156.85503601299752, "count": 232013, "self": 155.66494752799747, "children": { "RLTrainer._checkpoint": { "total": 1.1900884850000466, "count": 10, "self": 1.1900884850000466 } } }, "_update_policy": { "total": 362.5139640119987, "count": 97, "self": 295.91118476999566, "children": { "TorchPPOOptimizer.update": { "total": 66.60277924200307, "count": 2910, "self": 66.60277924200307 } } } } } } }, "trainer_threads": { "total": 8.440001693088561e-07, "count": 1, "self": 8.440001693088561e-07 }, "TrainerController._save_models": { "total": 0.10593431500001316, "count": 1, "self": 0.0017697859998406784, "children": { "RLTrainer._checkpoint": { "total": 0.10416452900017248, "count": 1, "self": 0.10416452900017248 } } } } } } }