{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4045264720916748, "min": 1.4045264720916748, "max": 1.4274543523788452, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69470.6875, "min": 68861.9453125, "max": 77868.78125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.16803953871499, "min": 76.63198757763975, "max": 398.0079365079365, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49269.0, "min": 48745.0, "max": 50149.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999900.0, "min": 49721.0, "max": 1999900.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999900.0, "min": 49721.0, "max": 1999900.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.502873182296753, "min": 0.06692254543304443, "max": 2.502873182296753, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1521.746826171875, "min": 8.365318298339844, "max": 1565.5361328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.037344164067977, "min": 1.8416928657293319, "max": 4.037344164067977, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2454.7052517533302, "min": 230.2116082161665, "max": 2472.2857999801636, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.037344164067977, "min": 1.8416928657293319, "max": 4.037344164067977, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2454.7052517533302, "min": 230.2116082161665, "max": 2472.2857999801636, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016560886787152007, "min": 0.01426722971437913, "max": 0.021550744418345858, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04968266036145602, "min": 0.029781745651659246, "max": 0.06465223325503758, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05964123014774587, "min": 0.02316232630982995, "max": 0.06021488967041175, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1789236904432376, "min": 0.0463246526196599, "max": 0.1789236904432376, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3534488822166672e-06, "min": 3.3534488822166672e-06, "max": 0.00029535742654752495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0060346646650002e-05, "min": 1.0060346646650002e-05, "max": 0.0008440113186628999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111778333333334, "min": 0.10111778333333334, "max": 0.19845247500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335335, "min": 0.20735929999999997, "max": 0.5813371000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.577738833333334e-05, "min": 6.577738833333334e-05, "max": 0.004922778502500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000197332165, "min": 0.000197332165, "max": 0.014068721290000002, "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": "1686810750", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686815563" }, "total": 4812.166789121, "count": 1, "self": 0.5879665530001148, "children": { "run_training.setup": { "total": 0.0554959510000117, "count": 1, "self": 0.0554959510000117 }, "TrainerController.start_learning": { "total": 4811.523326617, "count": 1, "self": 8.30740886591957, "children": { "TrainerController._reset_env": { "total": 1.7553328039998632, "count": 1, "self": 1.7553328039998632 }, "TrainerController.advance": { "total": 4801.338405773079, "count": 232573, "self": 8.444652020754802, "children": { "env_step": { "total": 3047.1231681521995, "count": 232573, "self": 2592.5215034943553, "children": { "SubprocessEnvManager._take_step": { "total": 448.9993177020019, "count": 232573, "self": 32.16665338879852, "children": { "TorchPolicy.evaluate": { "total": 416.8326643132034, "count": 222881, "self": 416.8326643132034 } } }, "workers": { "total": 5.602346955842222, "count": 232573, "self": 0.0, "children": { "worker_root": { "total": 4796.013130126937, "count": 232573, "is_parallel": true, "self": 2718.4704954040217, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020658340001773468, "count": 1, "is_parallel": true, "self": 0.0009420670000963582, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011237670000809885, "count": 2, "is_parallel": true, "self": 0.0011237670000809885 } } }, "UnityEnvironment.step": { "total": 0.04060263099995609, "count": 1, "is_parallel": true, "self": 0.00041838499987534306, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000304619999951683, "count": 1, "is_parallel": true, "self": 0.000304619999951683 }, "communicator.exchange": { "total": 0.03889995800000179, "count": 1, "is_parallel": true, "self": 0.03889995800000179 }, "steps_from_proto": { "total": 0.0009796680001272762, "count": 1, "is_parallel": true, "self": 0.00026724700001068413, "children": { "_process_rank_one_or_two_observation": { "total": 0.000712421000116592, "count": 2, "is_parallel": true, "self": 0.000712421000116592 } } } } } } }, "UnityEnvironment.step": { "total": 2077.542634722915, "count": 232572, "is_parallel": true, "self": 64.58114784890495, "children": { "UnityEnvironment._generate_step_input": { "total": 90.62263127400593, "count": 232572, "is_parallel": true, "self": 90.62263127400593 }, "communicator.exchange": { "total": 1777.227093147855, "count": 232572, "is_parallel": true, "self": 1777.227093147855 }, "steps_from_proto": { "total": 145.11176245214915, "count": 232572, "is_parallel": true, "self": 46.46312931086459, "children": { "_process_rank_one_or_two_observation": { "total": 98.64863314128456, "count": 465144, "is_parallel": true, "self": 98.64863314128456 } } } } } } } } } } }, "trainer_advance": { "total": 1745.770585600125, "count": 232573, "self": 13.792933550045973, "children": { "process_trajectory": { "total": 244.50521915707714, "count": 232573, "self": 242.7366969460768, "children": { "RLTrainer._checkpoint": { "total": 1.7685222110003451, "count": 10, "self": 1.7685222110003451 } } }, "_update_policy": { "total": 1487.472432893002, "count": 97, "self": 409.22595510601695, "children": { "TorchPPOOptimizer.update": { "total": 1078.246477786985, "count": 2910, "self": 1078.246477786985 } } } } } } }, "trainer_threads": { "total": 1.452000105928164e-06, "count": 1, "self": 1.452000105928164e-06 }, "TrainerController._save_models": { "total": 0.1221777220007425, "count": 1, "self": 0.002387911001278553, "children": { "RLTrainer._checkpoint": { "total": 0.11978981099946395, "count": 1, "self": 0.11978981099946395 } } } } } } }