{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073376655578613, "min": 1.4073376655578613, "max": 1.4285120964050293, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69594.2578125, "min": 68132.5, "max": 76555.3046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.59168241965973, "min": 91.56204379562044, "max": 410.57377049180326, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49510.0, "min": 48778.0, "max": 50176.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999999.0, "min": 49965.0, "max": 1999999.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999999.0, "min": 49965.0, "max": 1999999.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3788158893585205, "min": 0.16051530838012695, "max": 2.455166816711426, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1258.3935546875, "min": 19.422351837158203, "max": 1280.998291015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6355854417065365, "min": 1.7397327120146475, "max": 3.848707510981449, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1923.2246986627579, "min": 210.50765815377235, "max": 2007.6051265597343, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6355854417065365, "min": 1.7397327120146475, "max": 3.848707510981449, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1923.2246986627579, "min": 210.50765815377235, "max": 2007.6051265597343, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015474747291914859, "min": 0.014022106820630143, "max": 0.02102927019489774, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04642424187574458, "min": 0.028044213641260286, "max": 0.056329644157085565, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05281887708438768, "min": 0.02189279527713855, "max": 0.0668569100399812, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15845663125316303, "min": 0.0437855905542771, "max": 0.1829040851444006, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.240898919733332e-06, "min": 3.240898919733332e-06, "max": 0.0002953221015593, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.722696759199996e-06, "min": 9.722696759199996e-06, "max": 0.0008442378185874, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108026666666665, "min": 0.10108026666666665, "max": 0.19844070000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032408, "min": 0.20729615000000007, "max": 0.5814126000000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.390530666666666e-05, "min": 6.390530666666666e-05, "max": 0.0049221909300000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019171592, "min": 0.00019171592, "max": 0.01407248874, "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": "1719927584", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719930074" }, "total": 2490.1377658, "count": 1, "self": 0.43917210699964926, "children": { "run_training.setup": { "total": 0.05666279100000793, "count": 1, "self": 0.05666279100000793 }, "TrainerController.start_learning": { "total": 2489.6419309020002, "count": 1, "self": 4.554676629073583, "children": { "TrainerController._reset_env": { "total": 3.090423367000085, "count": 1, "self": 3.090423367000085 }, "TrainerController.advance": { "total": 2481.872291940926, "count": 231759, "self": 4.9896357879943025, "children": { "env_step": { "total": 1973.7233624139674, "count": 231759, "self": 1627.6138179399745, "children": { "SubprocessEnvManager._take_step": { "total": 343.0756268220216, "count": 231759, "self": 17.132067541924243, "children": { "TorchPolicy.evaluate": { "total": 325.94355928009736, "count": 222932, "self": 325.94355928009736 } } }, "workers": { "total": 3.033917651971251, "count": 231759, "self": 0.0, "children": { "worker_root": { "total": 2482.1059931638874, "count": 231759, "is_parallel": true, "self": 1172.0260468099414, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009282429999757369, "count": 1, "is_parallel": true, "self": 0.0002308439999296752, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006973990000460617, "count": 2, "is_parallel": true, "self": 0.0006973990000460617 } } }, "UnityEnvironment.step": { "total": 0.030755251000073258, "count": 1, "is_parallel": true, "self": 0.00038448000020707696, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002046409999820753, "count": 1, "is_parallel": true, "self": 0.0002046409999820753 }, "communicator.exchange": { "total": 0.029432107999923574, "count": 1, "is_parallel": true, "self": 0.029432107999923574 }, "steps_from_proto": { "total": 0.0007340219999605324, "count": 1, "is_parallel": true, "self": 0.0001957849999598693, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005382370000006631, "count": 2, "is_parallel": true, "self": 0.0005382370000006631 } } } } } } }, "UnityEnvironment.step": { "total": 1310.079946353946, "count": 231758, "is_parallel": true, "self": 39.82550032993322, "children": { "UnityEnvironment._generate_step_input": { "total": 87.40212698798825, "count": 231758, "is_parallel": true, "self": 87.40212698798825 }, "communicator.exchange": { "total": 1089.6059140130883, "count": 231758, "is_parallel": true, "self": 1089.6059140130883 }, "steps_from_proto": { "total": 93.24640502293641, "count": 231758, "is_parallel": true, "self": 35.45651869799701, "children": { "_process_rank_one_or_two_observation": { "total": 57.7898863249394, "count": 463516, "is_parallel": true, "self": 57.7898863249394 } } } } } } } } } } }, "trainer_advance": { "total": 503.1592937389644, "count": 231759, "self": 6.865649286986809, "children": { "process_trajectory": { "total": 160.74858253397974, "count": 231759, "self": 159.4486437479793, "children": { "RLTrainer._checkpoint": { "total": 1.299938786000439, "count": 10, "self": 1.299938786000439 } } }, "_update_policy": { "total": 335.5450619179978, "count": 97, "self": 271.1644347129958, "children": { "TorchPPOOptimizer.update": { "total": 64.38062720500204, "count": 2910, "self": 64.38062720500204 } } } } } } }, "trainer_threads": { "total": 1.151000105892308e-06, "count": 1, "self": 1.151000105892308e-06 }, "TrainerController._save_models": { "total": 0.1245378140001776, "count": 1, "self": 0.0021149750004951784, "children": { "RLTrainer._checkpoint": { "total": 0.12242283899968243, "count": 1, "self": 0.12242283899968243 } } } } } } }