{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4055912494659424, "min": 1.4055912494659424, "max": 1.4293824434280396, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69298.4609375, "min": 68389.6015625, "max": 78632.515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.2840909090909, "min": 72.33431085043988, "max": 400.752, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49455.0, "min": 49303.0, "max": 50278.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999991.0, "min": 49999.0, "max": 1999991.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999991.0, "min": 49999.0, "max": 1999991.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.481139659881592, "min": 0.1996988207101822, "max": 2.5650112628936768, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1528.382080078125, "min": 24.762653350830078, "max": 1669.506591796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7662480544153745, "min": 1.737678192315563, "max": 4.013000390366441, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2320.0088015198708, "min": 215.47209584712982, "max": 2622.4938257336617, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7662480544153745, "min": 1.737678192315563, "max": 4.013000390366441, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2320.0088015198708, "min": 215.47209584712982, "max": 2622.4938257336617, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01699187721145184, "min": 0.013666523584591535, "max": 0.01996272164324182, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05097563163435552, "min": 0.02733304716918307, "max": 0.05485654180738493, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056923088389966216, "min": 0.019846302177757024, "max": 0.06097604148089886, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17076926516989865, "min": 0.03969260435551405, "max": 0.18050543690721194, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8503487165833324e-06, "min": 3.8503487165833324e-06, "max": 0.00029529900156699995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1551046149749998e-05, "min": 1.1551046149749998e-05, "max": 0.0008440287186570999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128341666666667, "min": 0.10128341666666667, "max": 0.19843300000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30385025, "min": 0.2076965, "max": 0.5813429000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.404249166666667e-05, "min": 7.404249166666667e-05, "max": 0.004921806699999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000222127475, "min": 0.000222127475, "max": 0.01406901071, "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": "1715267449", "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": "1715271540" }, "total": 4091.189102212, "count": 1, "self": 0.5415943089997199, "children": { "run_training.setup": { "total": 0.07518303699998796, "count": 1, "self": 0.07518303699998796 }, "TrainerController.start_learning": { "total": 4090.572324866, "count": 1, "self": 7.188943778079647, "children": { "TrainerController._reset_env": { "total": 3.4571188820000316, "count": 1, "self": 3.4571188820000316 }, "TrainerController.advance": { "total": 4079.791853962921, "count": 233340, "self": 7.456218643150805, "children": { "env_step": { "total": 2642.9867234789276, "count": 233340, "self": 2212.119800031269, "children": { "SubprocessEnvManager._take_step": { "total": 425.97020370288124, "count": 233340, "self": 25.903391634985155, "children": { "TorchPolicy.evaluate": { "total": 400.0668120678961, "count": 222965, "self": 400.0668120678961 } } }, "workers": { "total": 4.8967197447777835, "count": 233340, "self": 0.0, "children": { "worker_root": { "total": 4079.0629299091033, "count": 233340, "is_parallel": true, "self": 2324.3888454011026, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013939730000629424, "count": 1, "is_parallel": true, "self": 0.00034563999997772044, "children": { "_process_rank_one_or_two_observation": { "total": 0.001048333000085222, "count": 2, "is_parallel": true, "self": 0.001048333000085222 } } }, "UnityEnvironment.step": { "total": 0.03472487999999885, "count": 1, "is_parallel": true, "self": 0.0004700380000031146, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002270759999873917, "count": 1, "is_parallel": true, "self": 0.0002270759999873917 }, "communicator.exchange": { "total": 0.03313220099994396, "count": 1, "is_parallel": true, "self": 0.03313220099994396 }, "steps_from_proto": { "total": 0.00089556500006438, "count": 1, "is_parallel": true, "self": 0.00024470000005294423, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006508650000114358, "count": 2, "is_parallel": true, "self": 0.0006508650000114358 } } } } } } }, "UnityEnvironment.step": { "total": 1754.6740845080008, "count": 233339, "is_parallel": true, "self": 55.88194237108473, "children": { "UnityEnvironment._generate_step_input": { "total": 102.45641629489967, "count": 233339, "is_parallel": true, "self": 102.45641629489967 }, "communicator.exchange": { "total": 1470.0702100211101, "count": 233339, "is_parallel": true, "self": 1470.0702100211101 }, "steps_from_proto": { "total": 126.26551582090622, "count": 233339, "is_parallel": true, "self": 41.4320239370802, "children": { "_process_rank_one_or_two_observation": { "total": 84.83349188382601, "count": 466678, "is_parallel": true, "self": 84.83349188382601 } } } } } } } } } } }, "trainer_advance": { "total": 1429.3489118408424, "count": 233340, "self": 11.334735557812792, "children": { "process_trajectory": { "total": 231.80257769602918, "count": 233340, "self": 230.40864755602934, "children": { "RLTrainer._checkpoint": { "total": 1.3939301399998385, "count": 10, "self": 1.3939301399998385 } } }, "_update_policy": { "total": 1186.2115985870005, "count": 97, "self": 314.33764145000055, "children": { "TorchPPOOptimizer.update": { "total": 871.8739571369999, "count": 2910, "self": 871.8739571369999 } } } } } } }, "trainer_threads": { "total": 1.0809999366756529e-06, "count": 1, "self": 1.0809999366756529e-06 }, "TrainerController._save_models": { "total": 0.13440716199966118, "count": 1, "self": 0.005817705999106693, "children": { "RLTrainer._checkpoint": { "total": 0.1285894560005545, "count": 1, "self": 0.1285894560005545 } } } } } } }