{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0026434659957886, "min": 1.0026434659957886, "max": 2.860476493835449, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9595.2978515625, "min": 9595.2978515625, "max": 29357.0703125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.184195518493652, "min": 0.3487732410430908, "max": 12.184195518493652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2375.918212890625, "min": 67.6620101928711, "max": 2450.476318359375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06846515056092947, "min": 0.06027657322359601, "max": 0.07338353172954692, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2738606022437179, "min": 0.2558685719046908, "max": 0.3669176586477346, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2102464163566337, "min": 0.13325321892910985, "max": 0.2739927209475462, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8409856654265347, "min": 0.5330128757164394, "max": 1.3699636047377308, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.40909090909091, "min": 3.409090909090909, "max": 24.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1074.0, "min": 150.0, "max": 1332.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.40909090909091, "min": 3.409090909090909, "max": 24.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1074.0, "min": 150.0, "max": 1332.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677682783", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/home/lorencl/git/ReinforcementLearning/venv/bin/mlagents-learn --env ./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id SnowballTarget1 --no-graphics --force ./config/ppo/SnowballTarget.yaml", "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": "1.20.0", "end_time_seconds": "1677682971" }, "total": 187.37651223600187, "count": 1, "self": 0.21812111300459947, "children": { "run_training.setup": { "total": 0.0076049419985793065, "count": 1, "self": 0.0076049419985793065 }, "TrainerController.start_learning": { "total": 187.1507861809987, "count": 1, "self": 0.29761615418465226, "children": { "TrainerController._reset_env": { "total": 0.3738448709991644, "count": 1, "self": 0.3738448709991644 }, "TrainerController.advance": { "total": 186.40754125581225, "count": 18208, "self": 0.13354714651723043, "children": { "env_step": { "total": 186.27399410929502, "count": 18208, "self": 144.2034901387451, "children": { "SubprocessEnvManager._take_step": { "total": 41.93021227058853, "count": 18208, "self": 0.6842378803157771, "children": { "TorchPolicy.evaluate": { "total": 41.24597439027275, "count": 18208, "self": 5.29764437614358, "children": { "TorchPolicy.sample_actions": { "total": 35.94833001412917, "count": 18208, "self": 35.94833001412917 } } } } }, "workers": { "total": 0.1402916999613808, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 186.7663553909406, "count": 18208, "is_parallel": true, "self": 90.89197152496854, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011645059967122506, "count": 1, "is_parallel": true, "self": 0.0003719079977599904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007925979989522602, "count": 10, "is_parallel": true, "self": 0.0007925979989522602 } } }, "UnityEnvironment.step": { "total": 0.01775563599949237, "count": 1, "is_parallel": true, "self": 0.0002186579986300785, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019157800124958158, "count": 1, "is_parallel": true, "self": 0.00019157800124958158 }, "communicator.exchange": { "total": 0.01668548300222028, "count": 1, "is_parallel": true, "self": 0.01668548300222028 }, "steps_from_proto": { "total": 0.000659916997392429, "count": 1, "is_parallel": true, "self": 0.00016703899746062234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004928779999318067, "count": 10, "is_parallel": true, "self": 0.0004928779999318067 } } } } } } }, "UnityEnvironment.step": { "total": 95.87438386597205, "count": 18207, "is_parallel": true, "self": 4.185385236160073, "children": { "UnityEnvironment._generate_step_input": { "total": 2.4288260328175966, "count": 18207, "is_parallel": true, "self": 2.4288260328175966 }, "communicator.exchange": { "total": 76.1872179210477, "count": 18207, "is_parallel": true, "self": 76.1872179210477 }, "steps_from_proto": { "total": 13.072954675946676, "count": 18207, "is_parallel": true, "self": 2.761003074301698, "children": { "_process_rank_one_or_two_observation": { "total": 10.311951601644978, "count": 182070, "is_parallel": true, "self": 10.311951601644978 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010729600035119802, "count": 1, "self": 0.00010729600035119802, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 186.32794998369718, "count": 93145, "is_parallel": true, "self": 0.9903635523369303, "children": { "process_trajectory": { "total": 99.85020210234507, "count": 93145, "is_parallel": true, "self": 99.4115592113485, "children": { "RLTrainer._checkpoint": { "total": 0.4386428909965616, "count": 4, "is_parallel": true, "self": 0.4386428909965616 } } }, "_update_policy": { "total": 85.48738432901519, "count": 90, "is_parallel": true, "self": 27.038048019021517, "children": { "TorchPPOOptimizer.update": { "total": 58.44933630999367, "count": 4587, "is_parallel": true, "self": 58.44933630999367 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0716766040022776, "count": 1, "self": 0.00047851000272203237, "children": { "RLTrainer._checkpoint": { "total": 0.07119809399955557, "count": 1, "self": 0.07119809399955557 } } } } } } }