{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4019502401351929, "min": 1.4019502401351929, "max": 1.427993655204773, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70453.609375, "min": 68164.453125, "max": 78835.390625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.82901554404145, "min": 75.5604900459418, "max": 382.5267175572519, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49116.0, "min": 48797.0, "max": 50111.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999969.0, "min": 49968.0, "max": 1999969.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999969.0, "min": 49968.0, "max": 1999969.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.384744882583618, "min": 0.22740785777568817, "max": 2.4597103595733643, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1380.767333984375, "min": 29.563020706176758, "max": 1571.779541015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6824671572560064, "min": 1.7531955755673923, "max": 3.9547142107871798, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2132.1484840512276, "min": 227.915424823761, "max": 2483.5905806422234, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6824671572560064, "min": 1.7531955755673923, "max": 3.9547142107871798, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2132.1484840512276, "min": 227.915424823761, "max": 2483.5905806422234, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015741434180191995, "min": 0.013480264104631108, "max": 0.020789566580788232, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04722430254057599, "min": 0.026960528209262216, "max": 0.06089238222399823, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050571165233850475, "min": 0.020452030437688035, "max": 0.0614801977450649, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15171349570155143, "min": 0.04090406087537607, "max": 0.17396727179487548, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.733698755466671e-06, "min": 3.733698755466671e-06, "max": 0.00029527860157379994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1201096266400013e-05, "min": 1.1201096266400013e-05, "max": 0.0008440422186526, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124453333333334, "min": 0.10124453333333334, "max": 0.19842620000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30373360000000005, "min": 0.2076214500000001, "max": 0.5813474000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.210221333333342e-05, "min": 7.210221333333342e-05, "max": 0.004921467380000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021630664000000025, "min": 0.00021630664000000025, "max": 0.01406923526, "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": "1708625252", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708627655" }, "total": 2403.0068459230006, "count": 1, "self": 0.3989398090002396, "children": { "run_training.setup": { "total": 0.04826039399995352, "count": 1, "self": 0.04826039399995352 }, "TrainerController.start_learning": { "total": 2402.5596457200004, "count": 1, "self": 4.42408907601839, "children": { "TrainerController._reset_env": { "total": 3.1724117440003283, "count": 1, "self": 3.1724117440003283 }, "TrainerController.advance": { "total": 2394.8488195399814, "count": 232742, "self": 4.811067841204476, "children": { "env_step": { "total": 1910.605372737804, "count": 232742, "self": 1583.0192061009075, "children": { "SubprocessEnvManager._take_step": { "total": 324.77751147589106, "count": 232742, "self": 17.050266290791114, "children": { "TorchPolicy.evaluate": { "total": 307.72724518509995, "count": 222956, "self": 307.72724518509995 } } }, "workers": { "total": 2.8086551610053903, "count": 232742, "self": 0.0, "children": { "worker_root": { "total": 2395.213974167149, "count": 232742, "is_parallel": true, "self": 1103.9676459368702, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010491440002624586, "count": 1, "is_parallel": true, "self": 0.00030866100041748723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007404829998449713, "count": 2, "is_parallel": true, "self": 0.0007404829998449713 } } }, "UnityEnvironment.step": { "total": 0.03240483999979915, "count": 1, "is_parallel": true, "self": 0.0004044369998155162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002283849999002996, "count": 1, "is_parallel": true, "self": 0.0002283849999002996 }, "communicator.exchange": { "total": 0.031026552000184893, "count": 1, "is_parallel": true, "self": 0.031026552000184893 }, "steps_from_proto": { "total": 0.0007454659998984425, "count": 1, "is_parallel": true, "self": 0.0002152780007236288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005301879991748137, "count": 2, "is_parallel": true, "self": 0.0005301879991748137 } } } } } } }, "UnityEnvironment.step": { "total": 1291.2463282302788, "count": 232741, "is_parallel": true, "self": 41.43117203722886, "children": { "UnityEnvironment._generate_step_input": { "total": 85.56319690105602, "count": 232741, "is_parallel": true, "self": 85.56319690105602 }, "communicator.exchange": { "total": 1072.1789512369833, "count": 232741, "is_parallel": true, "self": 1072.1789512369833 }, "steps_from_proto": { "total": 92.07300805501063, "count": 232741, "is_parallel": true, "self": 34.21838686204228, "children": { "_process_rank_one_or_two_observation": { "total": 57.85462119296835, "count": 465482, "is_parallel": true, "self": 57.85462119296835 } } } } } } } } } } }, "trainer_advance": { "total": 479.432378960973, "count": 232742, "self": 6.5324594319954485, "children": { "process_trajectory": { "total": 153.26792729797626, "count": 232742, "self": 152.02564915797666, "children": { "RLTrainer._checkpoint": { "total": 1.2422781399995984, "count": 10, "self": 1.2422781399995984 } } }, "_update_policy": { "total": 319.6319922310013, "count": 97, "self": 257.4808606139968, "children": { "TorchPPOOptimizer.update": { "total": 62.15113161700447, "count": 2910, "self": 62.15113161700447 } } } } } } }, "trainer_threads": { "total": 8.910001270123757e-07, "count": 1, "self": 8.910001270123757e-07 }, "TrainerController._save_models": { "total": 0.11432446900016657, "count": 1, "self": 0.001933411000209162, "children": { "RLTrainer._checkpoint": { "total": 0.11239105799995741, "count": 1, "self": 0.11239105799995741 } } } } } } }