{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4023973941802979, "min": 1.4023828506469727, "max": 1.4277911186218262, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70211.0234375, "min": 68987.9453125, "max": 77313.171875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.64958677685951, "min": 79.27652733118971, "max": 406.4390243902439, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49398.0, "min": 48840.0, "max": 50090.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49764.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49764.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4604721069335938, "min": 0.20990444719791412, "max": 2.484107255935669, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1488.585693359375, "min": 25.60834312438965, "max": 1488.585693359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.880130095816841, "min": 1.930128927846424, "max": 3.880130095816841, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2347.4787079691887, "min": 235.47572919726372, "max": 2347.4787079691887, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.880130095816841, "min": 1.930128927846424, "max": 3.880130095816841, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2347.4787079691887, "min": 235.47572919726372, "max": 2347.4787079691887, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01742317447400031, "min": 0.013733680191702055, "max": 0.019766374190415565, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05226952342200093, "min": 0.02746736038340411, "max": 0.05482692109532461, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054870248627331523, "min": 0.019770208342621724, "max": 0.059198234726985294, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16461074588199456, "min": 0.03954041668524345, "max": 0.17759470418095588, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.346448884550009e-06, "min": 3.346448884550009e-06, "max": 0.000295357276547575, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0039346653650028e-05, "min": 1.0039346653650028e-05, "max": 0.0008442163685945501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111545, "min": 0.10111545, "max": 0.19845242500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30334635, "min": 0.20736324999999997, "max": 0.5814054500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.566095500000016e-05, "min": 6.566095500000016e-05, "max": 0.004922776007500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019698286500000048, "min": 0.00019698286500000048, "max": 0.014072131955, "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": "1670978387", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1670980529" }, "total": 2142.197655036, "count": 1, "self": 0.39438902199981385, "children": { "run_training.setup": { "total": 0.10122951099998545, "count": 1, "self": 0.10122951099998545 }, "TrainerController.start_learning": { "total": 2141.7020365030003, "count": 1, "self": 3.5824251430144614, "children": { "TrainerController._reset_env": { "total": 10.065243643999963, "count": 1, "self": 10.065243643999963 }, "TrainerController.advance": { "total": 2127.9396072929862, "count": 232664, "self": 3.9180553459318617, "children": { "env_step": { "total": 1668.6683733050631, "count": 232664, "self": 1401.9288663971263, "children": { "SubprocessEnvManager._take_step": { "total": 264.24190320291336, "count": 232664, "self": 14.055262152935882, "children": { "TorchPolicy.evaluate": { "total": 250.18664104997748, "count": 222934, "self": 62.509993800893994, "children": { "TorchPolicy.sample_actions": { "total": 187.6766472490835, "count": 222934, "self": 187.6766472490835 } } } } }, "workers": { "total": 2.4976037050234368, "count": 232664, "self": 0.0, "children": { "worker_root": { "total": 2134.1453410400313, "count": 232664, "is_parallel": true, "self": 981.696058098036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00392558599997983, "count": 1, "is_parallel": true, "self": 0.00030985399996552587, "children": { "_process_rank_one_or_two_observation": { "total": 0.0036157320000143045, "count": 2, "is_parallel": true, "self": 0.0036157320000143045 } } }, "UnityEnvironment.step": { "total": 0.02619575400001395, "count": 1, "is_parallel": true, "self": 0.0002624850000643164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017906899995523418, "count": 1, "is_parallel": true, "self": 0.00017906899995523418 }, "communicator.exchange": { "total": 0.025078146999987894, "count": 1, "is_parallel": true, "self": 0.025078146999987894 }, "steps_from_proto": { "total": 0.0006760530000065046, "count": 1, "is_parallel": true, "self": 0.0002329449999933786, "children": { "_process_rank_one_or_two_observation": { "total": 0.000443108000013126, "count": 2, "is_parallel": true, "self": 0.000443108000013126 } } } } } } }, "UnityEnvironment.step": { "total": 1152.4492829419953, "count": 232663, "is_parallel": true, "self": 33.55941999104948, "children": { "UnityEnvironment._generate_step_input": { "total": 72.78539059803296, "count": 232663, "is_parallel": true, "self": 72.78539059803296 }, "communicator.exchange": { "total": 956.5800518360026, "count": 232663, "is_parallel": true, "self": 956.5800518360026 }, "steps_from_proto": { "total": 89.52442051691025, "count": 232663, "is_parallel": true, "self": 36.826965353867365, "children": { "_process_rank_one_or_two_observation": { "total": 52.69745516304289, "count": 465326, "is_parallel": true, "self": 52.69745516304289 } } } } } } } } } } }, "trainer_advance": { "total": 455.35317864199106, "count": 232664, "self": 5.773772380844036, "children": { "process_trajectory": { "total": 142.75822234014663, "count": 232664, "self": 142.29103196114704, "children": { "RLTrainer._checkpoint": { "total": 0.4671903789995895, "count": 4, "self": 0.4671903789995895 } } }, "_update_policy": { "total": 306.8211839210004, "count": 97, "self": 254.09697563800046, "children": { "TorchPPOOptimizer.update": { "total": 52.72420828299994, "count": 2910, "self": 52.72420828299994 } } } } } } }, "trainer_threads": { "total": 9.659997886046767e-07, "count": 1, "self": 9.659997886046767e-07 }, "TrainerController._save_models": { "total": 0.11475945699976364, "count": 1, "self": 0.0024415899997620727, "children": { "RLTrainer._checkpoint": { "total": 0.11231786700000157, "count": 1, "self": 0.11231786700000157 } } } } } } }