{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.419002652168274, "min": 1.419002652168274, "max": 1.4336585998535156, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70015.0078125, "min": 69644.9765625, "max": 77138.2265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.04444444444445, "min": 80.8983606557377, "max": 393.74015748031496, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49522.0, "min": 49085.0, "max": 50123.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999981.0, "min": 49720.0, "max": 1999981.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999981.0, "min": 49720.0, "max": 1999981.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.345958709716797, "min": 0.026557682082057, "max": 2.4552905559539795, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1161.24951171875, "min": 3.3462679386138916, "max": 1458.442626953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.426805532821501, "min": 1.855288378776066, "max": 3.8521291624729326, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1696.268738746643, "min": 233.7663357257843, "max": 2277.3595340251923, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.426805532821501, "min": 1.855288378776066, "max": 3.8521291624729326, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1696.268738746643, "min": 233.7663357257843, "max": 2277.3595340251923, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01618660277971584, "min": 0.013231132179013609, "max": 0.019874131717369892, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04855980833914752, "min": 0.026462264358027218, "max": 0.05543710958590964, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.055792152881622314, "min": 0.0228065116951863, "max": 0.06833089163733853, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16737645864486694, "min": 0.0456130233903726, "max": 0.20499267491201562, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.772898742399987e-06, "min": 3.772898742399987e-06, "max": 0.0002953864515378499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.131869622719996e-05, "min": 1.131869622719996e-05, "max": 0.0008441346186217997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012576, "min": 0.1012576, "max": 0.19846214999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037728, "min": 0.20765795000000004, "max": 0.5813781999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.275423999999982e-05, "min": 7.275423999999982e-05, "max": 0.004923261284999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021826271999999945, "min": 0.00021826271999999945, "max": 0.01407077218, "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": "1736535484", "python_version": "3.11.2 (main, Sep 14 2024, 03:00:30) [GCC 12.2.0]", "command_line_arguments": "/home/lucien/Workspace/deep-rl-hugging-face/.venv/bin/mlagents-learn ./Huggy.yaml --env=./envs/Huggy/Huggy.x86_64 --run-id=Huggy --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1736539714" }, "total": 4229.777110309005, "count": 1, "self": 0.2690794260124676, "children": { "run_training.setup": { "total": 0.017177205998450518, "count": 1, "self": 0.017177205998450518 }, "TrainerController.start_learning": { "total": 4229.490853676994, "count": 1, "self": 3.1951357410580385, "children": { "TrainerController._reset_env": { "total": 1.757877448995714, "count": 1, "self": 1.757877448995714 }, "TrainerController.advance": { "total": 4224.50203892494, "count": 232622, "self": 2.6429820155608468, "children": { "env_step": { "total": 3802.9597281361494, "count": 232622, "self": 3606.446267847874, "children": { "SubprocessEnvManager._take_step": { "total": 194.3614402624371, "count": 232622, "self": 13.616157618060242, "children": { "TorchPolicy.evaluate": { "total": 180.74528264437686, "count": 223017, "self": 180.74528264437686 } } }, "workers": { "total": 2.152020025838283, "count": 232622, "self": 0.0, "children": { "worker_root": { "total": 4222.5241382354, "count": 232622, "is_parallel": true, "self": 871.2681235457858, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000538847001735121, "count": 1, "is_parallel": true, "self": 0.00012182000500615686, "children": { "_process_rank_one_or_two_observation": { "total": 0.00041702699672896415, "count": 2, "is_parallel": true, "self": 0.00041702699672896415 } } }, "UnityEnvironment.step": { "total": 0.029837320995284244, "count": 1, "is_parallel": true, "self": 0.0001549629814689979, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003500400052871555, "count": 1, "is_parallel": true, "self": 0.0003500400052871555 }, "communicator.exchange": { "total": 0.028739330009557307, "count": 1, "is_parallel": true, "self": 0.028739330009557307 }, "steps_from_proto": { "total": 0.0005929879989707842, "count": 1, "is_parallel": true, "self": 0.00015834698569960892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004346410132711753, "count": 2, "is_parallel": true, "self": 0.0004346410132711753 } } } } } } }, "UnityEnvironment.step": { "total": 3351.256014689614, "count": 232621, "is_parallel": true, "self": 24.912083958523, "children": { "UnityEnvironment._generate_step_input": { "total": 250.86380107582954, "count": 232621, "is_parallel": true, "self": 250.86380107582954 }, "communicator.exchange": { "total": 2994.8188047677104, "count": 232621, "is_parallel": true, "self": 2994.8188047677104 }, "steps_from_proto": { "total": 80.66132488755102, "count": 232621, "is_parallel": true, "self": 23.57657541986555, "children": { "_process_rank_one_or_two_observation": { "total": 57.08474946768547, "count": 465242, "is_parallel": true, "self": 57.08474946768547 } } } } } } } } } } }, "trainer_advance": { "total": 418.8993287732301, "count": 232622, "self": 5.2829950310406275, "children": { "process_trajectory": { "total": 99.63399304414634, "count": 232622, "self": 99.09129381917592, "children": { "RLTrainer._checkpoint": { "total": 0.5426992249704199, "count": 10, "self": 0.5426992249704199 } } }, "_update_policy": { "total": 313.9823406980431, "count": 97, "self": 169.1170613021386, "children": { "TorchPPOOptimizer.update": { "total": 144.8652793959045, "count": 2910, "self": 144.8652793959045 } } } } } } }, "trainer_threads": { "total": 6.00994098931551e-07, "count": 1, "self": 6.00994098931551e-07 }, "TrainerController._save_models": { "total": 0.035800961006316356, "count": 1, "self": 0.000968530002865009, "children": { "RLTrainer._checkpoint": { "total": 0.03483243100345135, "count": 1, "self": 0.03483243100345135 } } } } } } }