{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4063880443572998, "min": 1.4063880443572998, "max": 1.4280123710632324, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69022.7109375, "min": 67943.3671875, "max": 77700.2265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.20242914979757, "min": 80.63071895424837, "max": 397.88188976377955, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49500.0, "min": 48805.0, "max": 50531.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49995.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49995.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4055700302124023, "min": 0.2757219970226288, "max": 2.4262635707855225, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1188.3515625, "min": 34.740970611572266, "max": 1450.77685546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6594449057270158, "min": 1.7627363808098293, "max": 3.9517849013460205, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1807.7657834291458, "min": 222.1047839820385, "max": 2347.360231399536, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6594449057270158, "min": 1.7627363808098293, "max": 3.9517849013460205, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1807.7657834291458, "min": 222.1047839820385, "max": 2347.360231399536, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014390847869253773, "min": 0.013039905866086578, "max": 0.021826041363480424, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04317254360776132, "min": 0.026079811732173157, "max": 0.05784549708090102, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04929005168378353, "min": 0.019915925959746044, "max": 0.05241654569076167, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1478701550513506, "min": 0.03983185191949209, "max": 0.157249637072285, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3453988848999936e-06, "min": 3.3453988848999936e-06, "max": 0.0002953446015517999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0036196654699981e-05, "min": 1.0036196654699981e-05, "max": 0.0008439820686726499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111510000000001, "min": 0.10111510000000001, "max": 0.19844820000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30334530000000004, "min": 0.20738374999999998, "max": 0.5813273499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.564348999999993e-05, "min": 6.564348999999993e-05, "max": 0.0049225651799999996, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001969304699999998, "min": 0.0001969304699999998, "max": 0.014068234764999998, "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": "1711363064", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711365628" }, "total": 2564.6766432020004, "count": 1, "self": 0.4430240240008061, "children": { "run_training.setup": { "total": 0.0822040969999307, "count": 1, "self": 0.0822040969999307 }, "TrainerController.start_learning": { "total": 2564.151415081, "count": 1, "self": 4.946883093024553, "children": { "TrainerController._reset_env": { "total": 2.981782206999924, "count": 1, "self": 2.981782206999924 }, "TrainerController.advance": { "total": 2556.1058000039757, "count": 232117, "self": 5.059691178963931, "children": { "env_step": { "total": 2059.8231920990943, "count": 232117, "self": 1707.640693808074, "children": { "SubprocessEnvManager._take_step": { "total": 348.88583408603495, "count": 232117, "self": 18.639614157988944, "children": { "TorchPolicy.evaluate": { "total": 330.246219928046, "count": 222978, "self": 330.246219928046 } } }, "workers": { "total": 3.296664204985177, "count": 232117, "self": 0.0, "children": { "worker_root": { "total": 2556.511436407847, "count": 232117, "is_parallel": true, "self": 1181.9643697598767, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009663810000120066, "count": 1, "is_parallel": true, "self": 0.00028515100007098226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006812299999410243, "count": 2, "is_parallel": true, "self": 0.0006812299999410243 } } }, "UnityEnvironment.step": { "total": 0.03140544100006082, "count": 1, "is_parallel": true, "self": 0.0003695720000678193, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002136030000201572, "count": 1, "is_parallel": true, "self": 0.0002136030000201572 }, "communicator.exchange": { "total": 0.030053416999976434, "count": 1, "is_parallel": true, "self": 0.030053416999976434 }, "steps_from_proto": { "total": 0.0007688489999964077, "count": 1, "is_parallel": true, "self": 0.00021853500004453963, "children": { "_process_rank_one_or_two_observation": { "total": 0.000550313999951868, "count": 2, "is_parallel": true, "self": 0.000550313999951868 } } } } } } }, "UnityEnvironment.step": { "total": 1374.5470666479705, "count": 232116, "is_parallel": true, "self": 41.32263772495071, "children": { "UnityEnvironment._generate_step_input": { "total": 92.16361531995847, "count": 232116, "is_parallel": true, "self": 92.16361531995847 }, "communicator.exchange": { "total": 1141.930236330079, "count": 232116, "is_parallel": true, "self": 1141.930236330079 }, "steps_from_proto": { "total": 99.13057727298258, "count": 232116, "is_parallel": true, "self": 37.95601494095331, "children": { "_process_rank_one_or_two_observation": { "total": 61.17456233202927, "count": 464232, "is_parallel": true, "self": 61.17456233202927 } } } } } } } } } } }, "trainer_advance": { "total": 491.22291672591734, "count": 232117, "self": 7.437410417919182, "children": { "process_trajectory": { "total": 164.8910756569976, "count": 232117, "self": 163.61179836599672, "children": { "RLTrainer._checkpoint": { "total": 1.2792772910008807, "count": 10, "self": 1.2792772910008807 } } }, "_update_policy": { "total": 318.89443065100056, "count": 97, "self": 255.0816976920055, "children": { "TorchPPOOptimizer.update": { "total": 63.81273295899507, "count": 2910, "self": 63.81273295899507 } } } } } } }, "trainer_threads": { "total": 7.809999260643963e-07, "count": 1, "self": 7.809999260643963e-07 }, "TrainerController._save_models": { "total": 0.1169489959997918, "count": 1, "self": 0.0019708089994310285, "children": { "RLTrainer._checkpoint": { "total": 0.11497818700036078, "count": 1, "self": 0.11497818700036078 } } } } } } }