{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3994526863098145, "min": 1.3994526863098145, "max": 1.4250130653381348, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69937.6484375, "min": 68200.296875, "max": 75459.453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.31669535283993, "min": 80.48613376835236, "max": 401.528, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48988.0, "min": 48988.0, "max": 50191.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49862.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49862.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4512810707092285, "min": -0.0021586164366453886, "max": 2.4729602336883545, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1424.1943359375, "min": -0.2676684260368347, "max": 1508.4461669921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.831680987870221, "min": 1.6473813275656393, "max": 3.9703786962821392, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2226.2066539525986, "min": 204.27528461813927, "max": 2342.247336268425, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.831680987870221, "min": 1.6473813275656393, "max": 3.9703786962821392, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2226.2066539525986, "min": 204.27528461813927, "max": 2342.247336268425, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017722855024314615, "min": 0.013244845148195357, "max": 0.01926078161850455, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.053168565072943846, "min": 0.026489690296390714, "max": 0.05778234485551365, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.055530765528480214, "min": 0.0224892641728123, "max": 0.06346712708473205, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16659229658544064, "min": 0.0449785283456246, "max": 0.1849807508289814, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6309487897166743e-06, "min": 3.6309487897166743e-06, "max": 0.00029536627654457503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0892846369150022e-05, "min": 1.0892846369150022e-05, "max": 0.0008444611685129498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121028333333333, "min": 0.10121028333333333, "max": 0.19845542500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30363085, "min": 0.20754655, "max": 0.58148705, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.039313833333346e-05, "min": 7.039313833333346e-05, "max": 0.004922925707499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002111794150000004, "min": 0.0002111794150000004, "max": 0.014076203794999999, "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": "1698668259", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698670588" }, "total": 2329.0647806419997, "count": 1, "self": 0.42542666599956647, "children": { "run_training.setup": { "total": 0.043762385000036375, "count": 1, "self": 0.043762385000036375 }, "TrainerController.start_learning": { "total": 2328.595591591, "count": 1, "self": 4.258302252162139, "children": { "TrainerController._reset_env": { "total": 7.604088033999915, "count": 1, "self": 7.604088033999915 }, "TrainerController.advance": { "total": 2316.635487827838, "count": 232408, "self": 4.420575910928619, "children": { "env_step": { "total": 1837.7512727579717, "count": 232408, "self": 1515.7021936389203, "children": { "SubprocessEnvManager._take_step": { "total": 319.3180452530544, "count": 232408, "self": 16.849247200131913, "children": { "TorchPolicy.evaluate": { "total": 302.46879805292247, "count": 223008, "self": 302.46879805292247 } } }, "workers": { "total": 2.7310338659970057, "count": 232408, "self": 0.0, "children": { "worker_root": { "total": 2321.216463854049, "count": 232408, "is_parallel": true, "self": 1084.166770472022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008377009999094298, "count": 1, "is_parallel": true, "self": 0.0002568749998772546, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005808260000321752, "count": 2, "is_parallel": true, "self": 0.0005808260000321752 } } }, "UnityEnvironment.step": { "total": 0.02890000100001089, "count": 1, "is_parallel": true, "self": 0.000290717999860135, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002011530000345374, "count": 1, "is_parallel": true, "self": 0.0002011530000345374 }, "communicator.exchange": { "total": 0.027761375999943994, "count": 1, "is_parallel": true, "self": 0.027761375999943994 }, "steps_from_proto": { "total": 0.0006467540001722227, "count": 1, "is_parallel": true, "self": 0.000163081000209786, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048367299996243673, "count": 2, "is_parallel": true, "self": 0.00048367299996243673 } } } } } } }, "UnityEnvironment.step": { "total": 1237.0496933820268, "count": 232407, "is_parallel": true, "self": 39.44456202092442, "children": { "UnityEnvironment._generate_step_input": { "total": 80.9487734470058, "count": 232407, "is_parallel": true, "self": 80.9487734470058 }, "communicator.exchange": { "total": 1028.0010500810847, "count": 232407, "is_parallel": true, "self": 1028.0010500810847 }, "steps_from_proto": { "total": 88.65530783301188, "count": 232407, "is_parallel": true, "self": 31.05698735523265, "children": { "_process_rank_one_or_two_observation": { "total": 57.598320477779225, "count": 464814, "is_parallel": true, "self": 57.598320477779225 } } } } } } } } } } }, "trainer_advance": { "total": 474.46363915893767, "count": 232408, "self": 6.314363298865828, "children": { "process_trajectory": { "total": 146.1984655430747, "count": 232408, "self": 145.0710937940746, "children": { "RLTrainer._checkpoint": { "total": 1.1273717490000763, "count": 10, "self": 1.1273717490000763 } } }, "_update_policy": { "total": 321.95081031699715, "count": 97, "self": 261.41864114200007, "children": { "TorchPPOOptimizer.update": { "total": 60.53216917499708, "count": 2910, "self": 60.53216917499708 } } } } } } }, "trainer_threads": { "total": 9.899999895424116e-07, "count": 1, "self": 9.899999895424116e-07 }, "TrainerController._save_models": { "total": 0.09771248700008073, "count": 1, "self": 0.0019055350003327476, "children": { "RLTrainer._checkpoint": { "total": 0.09580695199974798, "count": 1, "self": 0.09580695199974798 } } } } } } }