{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406241774559021, "min": 1.406241774559021, "max": 1.4256099462509155, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69810.0625, "min": 68555.2578125, "max": 75322.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 102.54469854469855, "min": 91.119926199262, "max": 399.344, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49324.0, "min": 48886.0, "max": 50095.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999970.0, "min": 49642.0, "max": 1999970.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999970.0, "min": 49642.0, "max": 1999970.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.358253240585327, "min": -0.008133839815855026, "max": 2.4052131175994873, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1134.31982421875, "min": -1.0085961818695068, "max": 1242.32373046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.763692933283824, "min": 1.7708677325638071, "max": 3.898620560677094, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1810.3363009095192, "min": 219.58759883791208, "max": 2046.0836837291718, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.763692933283824, "min": 1.7708677325638071, "max": 3.898620560677094, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1810.3363009095192, "min": 219.58759883791208, "max": 2046.0836837291718, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016715996153652667, "min": 0.013069727584176388, "max": 0.01962106506883477, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050147988460958005, "min": 0.026139455168352775, "max": 0.05535505848371637, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.047906379153331125, "min": 0.023437867965549232, "max": 0.05227772754927476, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14371913745999337, "min": 0.046875735931098464, "max": 0.14698508257667223, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.398148867316663e-06, "min": 3.398148867316663e-06, "max": 0.000295327426557525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0194446601949989e-05, "min": 1.0194446601949989e-05, "max": 0.0008441317686227496, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113268333333335, "min": 0.10113268333333335, "max": 0.19844247500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30339805000000003, "min": 0.20742600000000008, "max": 0.5813772500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.652089833333328e-05, "min": 6.652089833333328e-05, "max": 0.0049222795025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019956269499999985, "min": 0.00019956269499999985, "max": 0.014070724775000003, "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": "1740476573", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740479001" }, "total": 2428.2367960640004, "count": 1, "self": 0.4356923089999327, "children": { "run_training.setup": { "total": 0.02551753300008386, "count": 1, "self": 0.02551753300008386 }, "TrainerController.start_learning": { "total": 2427.775586222, "count": 1, "self": 4.266442970081698, "children": { "TrainerController._reset_env": { "total": 3.434774470000093, "count": 1, "self": 3.434774470000093 }, "TrainerController.advance": { "total": 2419.9617429189184, "count": 231588, "self": 4.603185976912755, "children": { "env_step": { "total": 1921.1714049529294, "count": 231588, "self": 1502.279281569898, "children": { "SubprocessEnvManager._take_step": { "total": 416.3173120479671, "count": 231588, "self": 15.654377411944097, "children": { "TorchPolicy.evaluate": { "total": 400.662934636023, "count": 222944, "self": 400.662934636023 } } }, "workers": { "total": 2.574811335064169, "count": 231588, "self": 0.0, "children": { "worker_root": { "total": 2420.564094483078, "count": 231588, "is_parallel": true, "self": 1192.1997386360572, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001422180000190565, "count": 1, "is_parallel": true, "self": 0.0005188720003843628, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009033079998062021, "count": 2, "is_parallel": true, "self": 0.0009033079998062021 } } }, "UnityEnvironment.step": { "total": 0.03199702699998852, "count": 1, "is_parallel": true, "self": 0.00035150200005773513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023514099984822678, "count": 1, "is_parallel": true, "self": 0.00023514099984822678 }, "communicator.exchange": { "total": 0.030623648000073445, "count": 1, "is_parallel": true, "self": 0.030623648000073445 }, "steps_from_proto": { "total": 0.0007867360000091139, "count": 1, "is_parallel": true, "self": 0.00021663600000465522, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005701000000044587, "count": 2, "is_parallel": true, "self": 0.0005701000000044587 } } } } } } }, "UnityEnvironment.step": { "total": 1228.3643558470208, "count": 231587, "is_parallel": true, "self": 37.608265071051164, "children": { "UnityEnvironment._generate_step_input": { "total": 80.16950956988853, "count": 231587, "is_parallel": true, "self": 80.16950956988853 }, "communicator.exchange": { "total": 1024.0658910470183, "count": 231587, "is_parallel": true, "self": 1024.0658910470183 }, "steps_from_proto": { "total": 86.52069015906272, "count": 231587, "is_parallel": true, "self": 30.196254849981415, "children": { "_process_rank_one_or_two_observation": { "total": 56.32443530908131, "count": 463174, "is_parallel": true, "self": 56.32443530908131 } } } } } } } } } } }, "trainer_advance": { "total": 494.187151989076, "count": 231588, "self": 6.284965793007586, "children": { "process_trajectory": { "total": 151.3677444390671, "count": 231588, "self": 150.0040856190676, "children": { "RLTrainer._checkpoint": { "total": 1.3636588199995003, "count": 10, "self": 1.3636588199995003 } } }, "_update_policy": { "total": 336.53444175700133, "count": 97, "self": 269.4969943370056, "children": { "TorchPPOOptimizer.update": { "total": 67.03744741999571, "count": 2910, "self": 67.03744741999571 } } } } } } }, "trainer_threads": { "total": 1.032999989547534e-06, "count": 1, "self": 1.032999989547534e-06 }, "TrainerController._save_models": { "total": 0.1126248300001862, "count": 1, "self": 0.001877055000022665, "children": { "RLTrainer._checkpoint": { "total": 0.11074777500016353, "count": 1, "self": 0.11074777500016353 } } } } } } }