{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4026015996932983, "min": 1.4025839567184448, "max": 1.4290491342544556, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70353.09375, "min": 68859.859375, "max": 77866.296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.45528455284553, "min": 77.56357927786499, "max": 399.816, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49480.0, "min": 48972.0, "max": 49984.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999952.0, "min": 49564.0, "max": 1999952.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999952.0, "min": 49564.0, "max": 1999952.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.450636863708496, "min": 0.17243583500385284, "max": 2.500789165496826, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1507.1417236328125, "min": 21.382043838500977, "max": 1541.156494140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7890401770428914, "min": 1.953467421233654, "max": 3.9197186510036204, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2330.259708881378, "min": 242.2299602329731, "max": 2422.7382606863976, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7890401770428914, "min": 1.953467421233654, "max": 3.9197186510036204, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2330.259708881378, "min": 242.2299602329731, "max": 2422.7382606863976, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016953699299806935, "min": 0.013851543538233575, "max": 0.019531500664015766, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05086109789942081, "min": 0.02808297210043141, "max": 0.05739308166375849, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.060504245882232986, "min": 0.021600659005343914, "max": 0.06237295183042685, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18151273764669895, "min": 0.044091955324014026, "max": 0.18711885549128054, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.757798747433342e-06, "min": 3.757798747433342e-06, "max": 0.0002953773015408999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1273396242300026e-05, "min": 1.1273396242300026e-05, "max": 0.0008442838685720499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125256666666665, "min": 0.10125256666666665, "max": 0.1984591, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30375769999999996, "min": 0.20765985000000003, "max": 0.5814279500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.250307666666681e-05, "min": 7.250307666666681e-05, "max": 0.004923109089999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021750923000000042, "min": 0.00021750923000000042, "max": 0.014073254705, "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": "1716989514", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn Huggy.yaml --env=../../trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --force --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716991959" }, "total": 2444.7680075590006, "count": 1, "self": 0.4254548130002149, "children": { "run_training.setup": { "total": 0.0516744420001487, "count": 1, "self": 0.0516744420001487 }, "TrainerController.start_learning": { "total": 2444.290878304, "count": 1, "self": 4.477600359644384, "children": { "TrainerController._reset_env": { "total": 2.1456645079997543, "count": 1, "self": 2.1456645079997543 }, "TrainerController.advance": { "total": 2437.5531223433563, "count": 232855, "self": 4.73177273805868, "children": { "env_step": { "total": 1920.842735868211, "count": 232855, "self": 1591.0967612540162, "children": { "SubprocessEnvManager._take_step": { "total": 326.82168487310355, "count": 232855, "self": 16.837169581251146, "children": { "TorchPolicy.evaluate": { "total": 309.9845152918524, "count": 222900, "self": 309.9845152918524 } } }, "workers": { "total": 2.924289741091343, "count": 232855, "self": 0.0, "children": { "worker_root": { "total": 2437.105938819135, "count": 232855, "is_parallel": true, "self": 1157.2934382556205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008573499999329215, "count": 1, "is_parallel": true, "self": 0.0002238530005342909, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006334969993986306, "count": 2, "is_parallel": true, "self": 0.0006334969993986306 } } }, "UnityEnvironment.step": { "total": 0.028664184999797726, "count": 1, "is_parallel": true, "self": 0.00038499399943248136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020722199951705988, "count": 1, "is_parallel": true, "self": 0.00020722199951705988 }, "communicator.exchange": { "total": 0.027337984000041615, "count": 1, "is_parallel": true, "self": 0.027337984000041615 }, "steps_from_proto": { "total": 0.0007339850008065696, "count": 1, "is_parallel": true, "self": 0.00019620500097516924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005377799998314003, "count": 2, "is_parallel": true, "self": 0.0005377799998314003 } } } } } } }, "UnityEnvironment.step": { "total": 1279.8125005635147, "count": 232854, "is_parallel": true, "self": 38.999480492653674, "children": { "UnityEnvironment._generate_step_input": { "total": 81.46255501106498, "count": 232854, "is_parallel": true, "self": 81.46255501106498 }, "communicator.exchange": { "total": 1068.9659686000905, "count": 232854, "is_parallel": true, "self": 1068.9659686000905 }, "steps_from_proto": { "total": 90.38449645970559, "count": 232854, "is_parallel": true, "self": 32.13786306354086, "children": { "_process_rank_one_or_two_observation": { "total": 58.246633396164725, "count": 465708, "is_parallel": true, "self": 58.246633396164725 } } } } } } } } } } }, "trainer_advance": { "total": 511.97861373708656, "count": 232855, "self": 6.725723983256103, "children": { "process_trajectory": { "total": 160.61884978183025, "count": 232855, "self": 159.05924600283106, "children": { "RLTrainer._checkpoint": { "total": 1.5596037789991897, "count": 10, "self": 1.5596037789991897 } } }, "_update_policy": { "total": 344.6340399720002, "count": 97, "self": 278.86025342299126, "children": { "TorchPPOOptimizer.update": { "total": 65.77378654900895, "count": 2910, "self": 65.77378654900895 } } } } } } }, "trainer_threads": { "total": 1.4299994290922768e-06, "count": 1, "self": 1.4299994290922768e-06 }, "TrainerController._save_models": { "total": 0.11448966300031316, "count": 1, "self": 0.0018803340008162195, "children": { "RLTrainer._checkpoint": { "total": 0.11260932899949694, "count": 1, "self": 0.11260932899949694 } } } } } } }