{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404692530632019, "min": 1.404692530632019, "max": 1.43025541305542, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69907.3359375, "min": 68725.6328125, "max": 76662.5234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.75583482944344, "min": 82.26, "max": 406.48387096774195, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49437.0, "min": 48972.0, "max": 50404.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999992.0, "min": 49995.0, "max": 1999992.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999992.0, "min": 49995.0, "max": 1999992.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3775999546051025, "min": 0.04123542085289955, "max": 2.477747917175293, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1324.3231201171875, "min": 5.071956634521484, "max": 1433.8487548828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7426162783718624, "min": 1.7184212561545333, "max": 3.9294212354041815, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2084.6372670531273, "min": 211.3658145070076, "max": 2272.4301658272743, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7426162783718624, "min": 1.7184212561545333, "max": 3.9294212354041815, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2084.6372670531273, "min": 211.3658145070076, "max": 2272.4301658272743, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01793272016285401, "min": 0.013450298637568872, "max": 0.019391151377931237, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.053798160488562036, "min": 0.026900597275137744, "max": 0.05663726482359834, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05660533433159193, "min": 0.022610695163408915, "max": 0.05907105778654416, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16981600299477578, "min": 0.04522139032681783, "max": 0.16981600299477578, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5746488084833433e-06, "min": 3.5746488084833433e-06, "max": 0.00029526607657797495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.072394642545003e-05, "min": 1.072394642545003e-05, "max": 0.0008438688187103998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119151666666666, "min": 0.10119151666666666, "max": 0.19842202499999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30357455, "min": 0.20751115000000003, "max": 0.5812896000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.945668166666685e-05, "min": 6.945668166666685e-05, "max": 0.0049212590475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020837004500000054, "min": 0.00020837004500000054, "max": 0.014066351040000001, "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": "1717099242", "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": "1717101667" }, "total": 2424.459008767, "count": 1, "self": 0.7313885309999932, "children": { "run_training.setup": { "total": 0.05888083800005006, "count": 1, "self": 0.05888083800005006 }, "TrainerController.start_learning": { "total": 2423.668739398, "count": 1, "self": 4.5038659970227855, "children": { "TrainerController._reset_env": { "total": 3.2019070369999554, "count": 1, "self": 3.2019070369999554 }, "TrainerController.advance": { "total": 2415.795793563978, "count": 232037, "self": 4.609857402972011, "children": { "env_step": { "total": 1909.3394433300173, "count": 232037, "self": 1573.0557172220522, "children": { "SubprocessEnvManager._take_step": { "total": 333.4411178499687, "count": 232037, "self": 16.86791578794646, "children": { "TorchPolicy.evaluate": { "total": 316.57320206202223, "count": 222894, "self": 316.57320206202223 } } }, "workers": { "total": 2.842608257996403, "count": 232037, "self": 0.0, "children": { "worker_root": { "total": 2416.472106921031, "count": 232037, "is_parallel": true, "self": 1150.2535950360007, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009100229999603471, "count": 1, "is_parallel": true, "self": 0.0002656120000210649, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006444109999392822, "count": 2, "is_parallel": true, "self": 0.0006444109999392822 } } }, "UnityEnvironment.step": { "total": 0.029528749000064636, "count": 1, "is_parallel": true, "self": 0.00037796200024331483, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021725099998093356, "count": 1, "is_parallel": true, "self": 0.00021725099998093356 }, "communicator.exchange": { "total": 0.028175340999951004, "count": 1, "is_parallel": true, "self": 0.028175340999951004 }, "steps_from_proto": { "total": 0.0007581949998893833, "count": 1, "is_parallel": true, "self": 0.00019414699988828943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005640480000010939, "count": 2, "is_parallel": true, "self": 0.0005640480000010939 } } } } } } }, "UnityEnvironment.step": { "total": 1266.2185118850302, "count": 232036, "is_parallel": true, "self": 38.64993796801468, "children": { "UnityEnvironment._generate_step_input": { "total": 79.94031465401076, "count": 232036, "is_parallel": true, "self": 79.94031465401076 }, "communicator.exchange": { "total": 1058.5425190430765, "count": 232036, "is_parallel": true, "self": 1058.5425190430765 }, "steps_from_proto": { "total": 89.08574021992831, "count": 232036, "is_parallel": true, "self": 31.603167360021985, "children": { "_process_rank_one_or_two_observation": { "total": 57.48257285990633, "count": 464072, "is_parallel": true, "self": 57.48257285990633 } } } } } } } } } } }, "trainer_advance": { "total": 501.8464928309887, "count": 232037, "self": 6.593519039893977, "children": { "process_trajectory": { "total": 154.17362836909479, "count": 232037, "self": 152.85260744109496, "children": { "RLTrainer._checkpoint": { "total": 1.3210209279998253, "count": 10, "self": 1.3210209279998253 } } }, "_update_policy": { "total": 341.07934542199996, "count": 97, "self": 276.34024355901, "children": { "TorchPPOOptimizer.update": { "total": 64.73910186298997, "count": 2910, "self": 64.73910186298997 } } } } } } }, "trainer_threads": { "total": 1.4039997040526941e-06, "count": 1, "self": 1.4039997040526941e-06 }, "TrainerController._save_models": { "total": 0.1671713959999579, "count": 1, "self": 0.002747016999819607, "children": { "RLTrainer._checkpoint": { "total": 0.1644243790001383, "count": 1, "self": 0.1644243790001383 } } } } } } }