{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405065655708313, "min": 1.405065655708313, "max": 1.4293980598449707, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71387.171875, "min": 67661.0, "max": 79093.3125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.46071428571429, "min": 77.60534591194968, "max": 396.6587301587302, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49538.0, "min": 48786.0, "max": 50155.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999916.0, "min": 49761.0, "max": 1999916.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999916.0, "min": 49761.0, "max": 1999916.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4247124195098877, "min": 0.16480138897895813, "max": 2.5119686126708984, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1355.414306640625, "min": 20.600173950195312, "max": 1512.9150390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.723474011864773, "min": 1.8918444848060607, "max": 4.044283063457087, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2081.421972632408, "min": 236.4805606007576, "max": 2368.0412348508835, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.723474011864773, "min": 1.8918444848060607, "max": 4.044283063457087, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2081.421972632408, "min": 236.4805606007576, "max": 2368.0412348508835, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017722844787123094, "min": 0.012345041956814384, "max": 0.020275521433601777, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.053168534361369285, "min": 0.024690083913628768, "max": 0.06058386262011481, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05074475482106208, "min": 0.021263205353170632, "max": 0.06009961470133729, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15223426446318625, "min": 0.042526410706341264, "max": 0.18029884410401187, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3437488854499973e-06, "min": 3.3437488854499973e-06, "max": 0.00029534955155014993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0031246656349992e-05, "min": 1.0031246656349992e-05, "max": 0.0008440600686466499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111455000000001, "min": 0.10111455000000001, "max": 0.19844984999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30334365, "min": 0.207426, "max": 0.5813533500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.561604499999996e-05, "min": 6.561604499999996e-05, "max": 0.0049226475150000015, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019684813499999988, "min": 0.00019684813499999988, "max": 0.014069532165000002, "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": "1688140741", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688143198" }, "total": 2457.0269087379997, "count": 1, "self": 0.4885828010001205, "children": { "run_training.setup": { "total": 0.08041533899995557, "count": 1, "self": 0.08041533899995557 }, "TrainerController.start_learning": { "total": 2456.4579105979997, "count": 1, "self": 4.28687293899884, "children": { "TrainerController._reset_env": { "total": 4.324525619000042, "count": 1, "self": 4.324525619000042 }, "TrainerController.advance": { "total": 2447.721782162001, "count": 232788, "self": 4.636305962948882, "children": { "env_step": { "total": 1904.6903729559913, "count": 232788, "self": 1608.8303816089665, "children": { "SubprocessEnvManager._take_step": { "total": 293.0220384319616, "count": 232788, "self": 16.688901937986316, "children": { "TorchPolicy.evaluate": { "total": 276.3331364939753, "count": 223028, "self": 276.3331364939753 } } }, "workers": { "total": 2.8379529150632834, "count": 232788, "self": 0.0, "children": { "worker_root": { "total": 2448.681068348942, "count": 232788, "is_parallel": true, "self": 1130.1866346609345, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009168400000589827, "count": 1, "is_parallel": true, "self": 0.00022733600007995847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006895039999790242, "count": 2, "is_parallel": true, "self": 0.0006895039999790242 } } }, "UnityEnvironment.step": { "total": 0.02872158800005309, "count": 1, "is_parallel": true, "self": 0.00035147200003393664, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002182499999889842, "count": 1, "is_parallel": true, "self": 0.0002182499999889842 }, "communicator.exchange": { "total": 0.027439925000066978, "count": 1, "is_parallel": true, "self": 0.027439925000066978 }, "steps_from_proto": { "total": 0.0007119409999631898, "count": 1, "is_parallel": true, "self": 0.0001957919998858415, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005161490000773483, "count": 2, "is_parallel": true, "self": 0.0005161490000773483 } } } } } } }, "UnityEnvironment.step": { "total": 1318.4944336880076, "count": 232787, "is_parallel": true, "self": 40.71286518411057, "children": { "UnityEnvironment._generate_step_input": { "total": 79.25401742289966, "count": 232787, "is_parallel": true, "self": 79.25401742289966 }, "communicator.exchange": { "total": 1101.3106113780884, "count": 232787, "is_parallel": true, "self": 1101.3106113780884 }, "steps_from_proto": { "total": 97.21693970290903, "count": 232787, "is_parallel": true, "self": 34.08795629502106, "children": { "_process_rank_one_or_two_observation": { "total": 63.12898340788797, "count": 465574, "is_parallel": true, "self": 63.12898340788797 } } } } } } } } } } }, "trainer_advance": { "total": 538.3951032430608, "count": 232788, "self": 6.674442535042772, "children": { "process_trajectory": { "total": 140.48584983701767, "count": 232788, "self": 139.02701554201826, "children": { "RLTrainer._checkpoint": { "total": 1.4588342949994058, "count": 10, "self": 1.4588342949994058 } } }, "_update_policy": { "total": 391.2348108710004, "count": 97, "self": 329.97851800499916, "children": { "TorchPPOOptimizer.update": { "total": 61.25629286600122, "count": 2910, "self": 61.25629286600122 } } } } } } }, "trainer_threads": { "total": 1.02400008472614e-06, "count": 1, "self": 1.02400008472614e-06 }, "TrainerController._save_models": { "total": 0.1247288539998408, "count": 1, "self": 0.002033097999628808, "children": { "RLTrainer._checkpoint": { "total": 0.12269575600021199, "count": 1, "self": 0.12269575600021199 } } } } } } }