{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4075688123703003, "min": 1.4075688123703003, "max": 1.4285122156143188, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71679.03125, "min": 68364.5703125, "max": 77729.09375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.84860557768924, "min": 84.80895008605852, "max": 387.6666666666667, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49120.0, "min": 48728.0, "max": 50113.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999982.0, "min": 49614.0, "max": 1999982.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999982.0, "min": 49614.0, "max": 1999982.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3847496509552, "min": 0.09954458475112915, "max": 2.4577646255493164, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1197.144287109375, "min": 12.741706848144531, "max": 1412.72705078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5873290089022114, "min": 1.797777979169041, "max": 3.9217323249578477, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1800.8391624689102, "min": 230.11558133363724, "max": 2234.322725057602, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5873290089022114, "min": 1.797777979169041, "max": 3.9217323249578477, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1800.8391624689102, "min": 230.11558133363724, "max": 2234.322725057602, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015615850713867176, "min": 0.01354615216065819, "max": 0.019765445217490196, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04684755214160153, "min": 0.02709230432131638, "max": 0.0570137973933015, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049910151296191745, "min": 0.02261923644691706, "max": 0.05762584081126584, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14973045388857523, "min": 0.04523847289383412, "max": 0.1728775224337975, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.407198864299996e-06, "min": 3.407198864299996e-06, "max": 0.000295327876557375, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0221596592899988e-05, "min": 1.0221596592899988e-05, "max": 0.0008441017686327499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113570000000001, "min": 0.10113570000000001, "max": 0.19844262499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30340710000000004, "min": 0.2074566, "max": 0.5813672500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.667142999999998e-05, "min": 6.667142999999998e-05, "max": 0.0049222869875, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002000142899999999, "min": 0.0002000142899999999, "max": 0.014070225775, "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": "1672093643", "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": "1672095857" }, "total": 2213.885561085, "count": 1, "self": 0.3911976540002797, "children": { "run_training.setup": { "total": 0.12059809400000177, "count": 1, "self": 0.12059809400000177 }, "TrainerController.start_learning": { "total": 2213.373765337, "count": 1, "self": 3.650775316947602, "children": { "TrainerController._reset_env": { "total": 8.922006678999992, "count": 1, "self": 8.922006678999992 }, "TrainerController.advance": { "total": 2200.6851427870524, "count": 232188, "self": 3.9802562822142136, "children": { "env_step": { "total": 1730.4238425579172, "count": 232188, "self": 1451.3601035060362, "children": { "SubprocessEnvManager._take_step": { "total": 276.5488270619701, "count": 232188, "self": 14.115413553918643, "children": { "TorchPolicy.evaluate": { "total": 262.43341350805144, "count": 223031, "self": 65.50539099014873, "children": { "TorchPolicy.sample_actions": { "total": 196.92802251790272, "count": 223031, "self": 196.92802251790272 } } } } }, "workers": { "total": 2.5149119899108427, "count": 232188, "self": 0.0, "children": { "worker_root": { "total": 2205.7311081099992, "count": 232188, "is_parallel": true, "self": 1011.9623151670553, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019471150000072157, "count": 1, "is_parallel": true, "self": 0.0003418679999640517, "children": { "_process_rank_one_or_two_observation": { "total": 0.001605247000043164, "count": 2, "is_parallel": true, "self": 0.001605247000043164 } } }, "UnityEnvironment.step": { "total": 0.02695964500003356, "count": 1, "is_parallel": true, "self": 0.00029898699995101197, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017659700006333878, "count": 1, "is_parallel": true, "self": 0.00017659700006333878 }, "communicator.exchange": { "total": 0.02568578900002194, "count": 1, "is_parallel": true, "self": 0.02568578900002194 }, "steps_from_proto": { "total": 0.0007982719999972687, "count": 1, "is_parallel": true, "self": 0.00024614100004782813, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005521309999494406, "count": 2, "is_parallel": true, "self": 0.0005521309999494406 } } } } } } }, "UnityEnvironment.step": { "total": 1193.768792942944, "count": 232187, "is_parallel": true, "self": 34.098205399021026, "children": { "UnityEnvironment._generate_step_input": { "total": 75.06756212893242, "count": 232187, "is_parallel": true, "self": 75.06756212893242 }, "communicator.exchange": { "total": 992.9145653389868, "count": 232187, "is_parallel": true, "self": 992.9145653389868 }, "steps_from_proto": { "total": 91.68846007600371, "count": 232187, "is_parallel": true, "self": 37.667164306869836, "children": { "_process_rank_one_or_two_observation": { "total": 54.02129576913387, "count": 464374, "is_parallel": true, "self": 54.02129576913387 } } } } } } } } } } }, "trainer_advance": { "total": 466.2810439469213, "count": 232188, "self": 6.005492284914112, "children": { "process_trajectory": { "total": 146.86850407000622, "count": 232188, "self": 145.664905269006, "children": { "RLTrainer._checkpoint": { "total": 1.2035988010002256, "count": 10, "self": 1.2035988010002256 } } }, "_update_policy": { "total": 313.40704759200094, "count": 97, "self": 259.76940556700356, "children": { "TorchPPOOptimizer.update": { "total": 53.637642024997376, "count": 2910, "self": 53.637642024997376 } } } } } } }, "trainer_threads": { "total": 9.119999049289618e-07, "count": 1, "self": 9.119999049289618e-07 }, "TrainerController._save_models": { "total": 0.11583964200008268, "count": 1, "self": 0.0019406060000619618, "children": { "RLTrainer._checkpoint": { "total": 0.11389903600002071, "count": 1, "self": 0.11389903600002071 } } } } } } }