{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4012993574142456, "min": 1.4012993574142456, "max": 1.4264063835144043, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71736.71875, "min": 67558.5859375, "max": 78826.2109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.44808743169399, "min": 81.72396694214876, "max": 376.34586466165416, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49656.0, "min": 49091.0, "max": 50054.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999501.0, "min": 49866.0, "max": 1999501.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999501.0, "min": 49866.0, "max": 1999501.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4383249282836914, "min": 0.12324665486812592, "max": 2.5127079486846924, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1338.640380859375, "min": 16.268558502197266, "max": 1485.1988525390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7872171875340475, "min": 1.778839255146908, "max": 4.081650724349013, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2079.182235956192, "min": 234.80678167939186, "max": 2316.120690524578, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7872171875340475, "min": 1.778839255146908, "max": 4.081650724349013, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2079.182235956192, "min": 234.80678167939186, "max": 2316.120690524578, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01680246840826132, "min": 0.013834860115700091, "max": 0.020430545811905176, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050407405224783965, "min": 0.027669720231400182, "max": 0.056993336183465235, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05269823479983541, "min": 0.024726837780326603, "max": 0.06981965427597364, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15809470439950624, "min": 0.04945367556065321, "max": 0.18635289234419664, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3595488801833297e-06, "min": 3.3595488801833297e-06, "max": 0.0002953383015539, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0078646640549989e-05, "min": 1.0078646640549989e-05, "max": 0.0008442738185754, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111981666666665, "min": 0.10111981666666665, "max": 0.19844610000000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335945, "min": 0.20742199999999997, "max": 0.5814246000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.587885166666663e-05, "min": 6.587885166666663e-05, "max": 0.004922460390000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019763655499999987, "min": 0.00019763655499999987, "max": 0.014073087539999998, "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": "1730773833", "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": "1730776353" }, "total": 2520.194457716, "count": 1, "self": 0.4274406730000919, "children": { "run_training.setup": { "total": 0.057249303999981294, "count": 1, "self": 0.057249303999981294 }, "TrainerController.start_learning": { "total": 2519.709767739, "count": 1, "self": 4.7046428850003394, "children": { "TrainerController._reset_env": { "total": 5.784914020000031, "count": 1, "self": 5.784914020000031 }, "TrainerController.advance": { "total": 2509.097582164, "count": 232495, "self": 4.827348179924229, "children": { "env_step": { "total": 1987.3367797280728, "count": 232495, "self": 1561.440398268026, "children": { "SubprocessEnvManager._take_step": { "total": 422.959805046037, "count": 232495, "self": 16.354032573145275, "children": { "TorchPolicy.evaluate": { "total": 406.6057724728917, "count": 223046, "self": 406.6057724728917 } } }, "workers": { "total": 2.9365764140096644, "count": 232495, "self": 0.0, "children": { "worker_root": { "total": 2512.1919393170674, "count": 232495, "is_parallel": true, "self": 1246.8975913751071, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000896710000006351, "count": 1, "is_parallel": true, "self": 0.0002578860000426175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006388239999637335, "count": 2, "is_parallel": true, "self": 0.0006388239999637335 } } }, "UnityEnvironment.step": { "total": 0.031003452999982528, "count": 1, "is_parallel": true, "self": 0.000430529999960072, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019252700002425627, "count": 1, "is_parallel": true, "self": 0.00019252700002425627 }, "communicator.exchange": { "total": 0.029624654999963695, "count": 1, "is_parallel": true, "self": 0.029624654999963695 }, "steps_from_proto": { "total": 0.0007557410000345044, "count": 1, "is_parallel": true, "self": 0.00019868300006464779, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005570579999698566, "count": 2, "is_parallel": true, "self": 0.0005570579999698566 } } } } } } }, "UnityEnvironment.step": { "total": 1265.2943479419603, "count": 232494, "is_parallel": true, "self": 38.46649110493581, "children": { "UnityEnvironment._generate_step_input": { "total": 82.97311350803614, "count": 232494, "is_parallel": true, "self": 82.97311350803614 }, "communicator.exchange": { "total": 1052.5167579870422, "count": 232494, "is_parallel": true, "self": 1052.5167579870422 }, "steps_from_proto": { "total": 91.3379853419462, "count": 232494, "is_parallel": true, "self": 34.41701590603776, "children": { "_process_rank_one_or_two_observation": { "total": 56.92096943590843, "count": 464988, "is_parallel": true, "self": 56.92096943590843 } } } } } } } } } } }, "trainer_advance": { "total": 516.9334542560028, "count": 232495, "self": 6.769735394061456, "children": { "process_trajectory": { "total": 172.64709063894196, "count": 232495, "self": 171.36738280294213, "children": { "RLTrainer._checkpoint": { "total": 1.2797078359998295, "count": 10, "self": 1.2797078359998295 } } }, "_update_policy": { "total": 337.51662822299943, "count": 97, "self": 270.7804913649865, "children": { "TorchPPOOptimizer.update": { "total": 66.73613685801291, "count": 2910, "self": 66.73613685801291 } } } } } } }, "trainer_threads": { "total": 9.54999904934084e-07, "count": 1, "self": 9.54999904934084e-07 }, "TrainerController._save_models": { "total": 0.12262771499990777, "count": 1, "self": 0.0020920040001328744, "children": { "RLTrainer._checkpoint": { "total": 0.12053571099977489, "count": 1, "self": 0.12053571099977489 } } } } } } }