{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4082492589950562, "min": 1.4082492589950562, "max": 1.4261722564697266, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70933.515625, "min": 68573.9609375, "max": 78944.2734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 78.96031746031746, "min": 68.78351955307262, "max": 388.2692307692308, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49745.0, "min": 48838.0, "max": 50475.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999715.0, "min": 49855.0, "max": 1999715.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999715.0, "min": 49855.0, "max": 1999715.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4907114505767822, "min": 0.0657123327255249, "max": 2.5414974689483643, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1569.148193359375, "min": 8.476890563964844, "max": 1759.378173828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8400393267472586, "min": 1.8014928010082984, "max": 4.0708517725073445, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2419.224775850773, "min": 232.3925713300705, "max": 2799.3455988168716, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8400393267472586, "min": 1.8014928010082984, "max": 4.0708517725073445, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2419.224775850773, "min": 232.3925713300705, "max": 2799.3455988168716, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01503198719648127, "min": 0.013607901184877846, "max": 0.019357518792094196, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04509596158944381, "min": 0.027215802369755692, "max": 0.05545685913530179, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05877684739728769, "min": 0.022502900287508964, "max": 0.06187217806776365, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17633054219186306, "min": 0.04500580057501793, "max": 0.18561653420329094, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7926987358000005e-06, "min": 3.7926987358000005e-06, "max": 0.00029534587655137497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1378096207400001e-05, "min": 1.1378096207400001e-05, "max": 0.0008439844686718499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126420000000003, "min": 0.10126420000000003, "max": 0.19844862499999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037926000000001, "min": 0.20767495000000002, "max": 0.58132815, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.308358000000002e-05, "min": 7.308358000000002e-05, "max": 0.0049225863875, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021925074000000007, "min": 0.00021925074000000007, "max": 0.014068274684999998, "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": "1696839226", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1696841933" }, "total": 2706.5561718299996, "count": 1, "self": 0.8310734949996004, "children": { "run_training.setup": { "total": 0.0505143020000105, "count": 1, "self": 0.0505143020000105 }, "TrainerController.start_learning": { "total": 2705.674584033, "count": 1, "self": 4.918478860932282, "children": { "TrainerController._reset_env": { "total": 7.987078443000087, "count": 1, "self": 7.987078443000087 }, "TrainerController.advance": { "total": 2692.6101145430675, "count": 233728, "self": 5.170828087029804, "children": { "env_step": { "total": 2070.0126661120826, "count": 233728, "self": 1712.47303375702, "children": { "SubprocessEnvManager._take_step": { "total": 354.31803769701037, "count": 233728, "self": 17.940462234033134, "children": { "TorchPolicy.evaluate": { "total": 336.37757546297723, "count": 223012, "self": 336.37757546297723 } } }, "workers": { "total": 3.221594658052254, "count": 233728, "self": 0.0, "children": { "worker_root": { "total": 2697.3612148970087, "count": 233728, "is_parallel": true, "self": 1304.671650688022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011792159999686191, "count": 1, "is_parallel": true, "self": 0.0003858889999719395, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007933269999966797, "count": 2, "is_parallel": true, "self": 0.0007933269999966797 } } }, "UnityEnvironment.step": { "total": 0.029454385999997612, "count": 1, "is_parallel": true, "self": 0.00035923599989473587, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023527500002273882, "count": 1, "is_parallel": true, "self": 0.00023527500002273882 }, "communicator.exchange": { "total": 0.028015600999992785, "count": 1, "is_parallel": true, "self": 0.028015600999992785 }, "steps_from_proto": { "total": 0.0008442740000873528, "count": 1, "is_parallel": true, "self": 0.00026854800000819523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005757260000791575, "count": 2, "is_parallel": true, "self": 0.0005757260000791575 } } } } } } }, "UnityEnvironment.step": { "total": 1392.6895642089867, "count": 233727, "is_parallel": true, "self": 42.07368748934368, "children": { "UnityEnvironment._generate_step_input": { "total": 93.59794064982304, "count": 233727, "is_parallel": true, "self": 93.59794064982304 }, "communicator.exchange": { "total": 1148.8927181779077, "count": 233727, "is_parallel": true, "self": 1148.8927181779077 }, "steps_from_proto": { "total": 108.12521789191203, "count": 233727, "is_parallel": true, "self": 41.82488775403999, "children": { "_process_rank_one_or_two_observation": { "total": 66.30033013787204, "count": 467454, "is_parallel": true, "self": 66.30033013787204 } } } } } } } } } } }, "trainer_advance": { "total": 617.4266203439552, "count": 233728, "self": 7.02502114300637, "children": { "process_trajectory": { "total": 170.6003631389483, "count": 233728, "self": 169.29696213394823, "children": { "RLTrainer._checkpoint": { "total": 1.3034010050000688, "count": 10, "self": 1.3034010050000688 } } }, "_update_policy": { "total": 439.8012360620005, "count": 97, "self": 375.77599135099524, "children": { "TorchPPOOptimizer.update": { "total": 64.02524471100526, "count": 2910, "self": 64.02524471100526 } } } } } } }, "trainer_threads": { "total": 1.2959999367012642e-06, "count": 1, "self": 1.2959999367012642e-06 }, "TrainerController._save_models": { "total": 0.15891089000024294, "count": 1, "self": 0.0029439520003506914, "children": { "RLTrainer._checkpoint": { "total": 0.15596693799989225, "count": 1, "self": 0.15596693799989225 } } } } } } }