{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40499746799469, "min": 1.40499746799469, "max": 1.4270411729812622, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70403.015625, "min": 66887.8984375, "max": 79451.0859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.61871750433275, "min": 77.93690851735016, "max": 409.9349593495935, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49402.0, "min": 48691.0, "max": 50422.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49911.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49911.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.521538019180298, "min": -0.041609592735767365, "max": 2.521538019180298, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1454.927490234375, "min": -5.0763702392578125, "max": 1551.7802734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8972946259756434, "min": 1.7280662186810227, "max": 3.944243610892075, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2248.7389991879463, "min": 210.82407867908478, "max": 2414.3300580382347, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8972946259756434, "min": 1.7280662186810227, "max": 3.944243610892075, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2248.7389991879463, "min": 210.82407867908478, "max": 2414.3300580382347, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015955473523232892, "min": 0.012652593932997055, "max": 0.02178045403949606, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04786642056969868, "min": 0.02530518786599411, "max": 0.055620537660433914, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057723105284902786, "min": 0.02484036556755503, "max": 0.06012814649277263, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17316931585470835, "min": 0.04968073113511006, "max": 0.1803844394783179, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.711948762716661e-06, "min": 3.711948762716661e-06, "max": 0.000295287001571, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1135846288149984e-05, "min": 1.1135846288149984e-05, "max": 0.0008439274686908502, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123728333333333, "min": 0.10123728333333333, "max": 0.19842900000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30371185, "min": 0.20762119999999995, "max": 0.58130915, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.174043833333324e-05, "min": 7.174043833333324e-05, "max": 0.004921607100000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021522131499999972, "min": 0.00021522131499999972, "max": 0.014067326585000001, "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": "1731414470", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731416947" }, "total": 2477.214544819, "count": 1, "self": 0.6803171319998, "children": { "run_training.setup": { "total": 0.05676662200005467, "count": 1, "self": 0.05676662200005467 }, "TrainerController.start_learning": { "total": 2476.477461065, "count": 1, "self": 4.669920277929123, "children": { "TrainerController._reset_env": { "total": 5.819878954999922, "count": 1, "self": 5.819878954999922 }, "TrainerController.advance": { "total": 2465.8158984220704, "count": 232906, "self": 4.506802633013649, "children": { "env_step": { "total": 1937.081980278075, "count": 232906, "self": 1523.0714882500324, "children": { "SubprocessEnvManager._take_step": { "total": 411.15909716803094, "count": 232906, "self": 16.00131816697865, "children": { "TorchPolicy.evaluate": { "total": 395.1577790010523, "count": 222929, "self": 395.1577790010523 } } }, "workers": { "total": 2.8513948600116237, "count": 232906, "self": 0.0, "children": { "worker_root": { "total": 2469.0655501289975, "count": 232906, "is_parallel": true, "self": 1230.9037850818825, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008787120000306459, "count": 1, "is_parallel": true, "self": 0.0002554999999802021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006232120000504437, "count": 2, "is_parallel": true, "self": 0.0006232120000504437 } } }, "UnityEnvironment.step": { "total": 0.04217322200008766, "count": 1, "is_parallel": true, "self": 0.00036885000008624047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018017899992628372, "count": 1, "is_parallel": true, "self": 0.00018017899992628372 }, "communicator.exchange": { "total": 0.04086405999998988, "count": 1, "is_parallel": true, "self": 0.04086405999998988 }, "steps_from_proto": { "total": 0.0007601330000852613, "count": 1, "is_parallel": true, "self": 0.00020483300022533513, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005552999998599262, "count": 2, "is_parallel": true, "self": 0.0005552999998599262 } } } } } } }, "UnityEnvironment.step": { "total": 1238.161765047115, "count": 232905, "is_parallel": true, "self": 37.95308625410212, "children": { "UnityEnvironment._generate_step_input": { "total": 79.70567165310649, "count": 232905, "is_parallel": true, "self": 79.70567165310649 }, "communicator.exchange": { "total": 1031.6209711169126, "count": 232905, "is_parallel": true, "self": 1031.6209711169126 }, "steps_from_proto": { "total": 88.88203602299393, "count": 232905, "is_parallel": true, "self": 30.93070421909897, "children": { "_process_rank_one_or_two_observation": { "total": 57.95133180389496, "count": 465810, "is_parallel": true, "self": 57.95133180389496 } } } } } } } } } } }, "trainer_advance": { "total": 524.2271155109817, "count": 232906, "self": 6.917343519042902, "children": { "process_trajectory": { "total": 172.48379062793708, "count": 232906, "self": 170.92271961293682, "children": { "RLTrainer._checkpoint": { "total": 1.561071015000266, "count": 10, "self": 1.561071015000266 } } }, "_update_policy": { "total": 344.8259813640017, "count": 97, "self": 277.04446155499363, "children": { "TorchPPOOptimizer.update": { "total": 67.78151980900805, "count": 2910, "self": 67.78151980900805 } } } } } } }, "trainer_threads": { "total": 1.446000169380568e-06, "count": 1, "self": 1.446000169380568e-06 }, "TrainerController._save_models": { "total": 0.17176196400032495, "count": 1, "self": 0.0031708580004305986, "children": { "RLTrainer._checkpoint": { "total": 0.16859110599989435, "count": 1, "self": 0.16859110599989435 } } } } } } }