{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9534351825714111, "min": 0.9462946057319641, "max": 2.866647243499756, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9134.8623046875, "min": 9134.8623046875, "max": 29451.93359375, "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": 12.95472526550293, "min": 0.43062466382980347, "max": 12.95472526550293, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.17138671875, "min": 83.54118347167969, "max": 2602.42138671875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06999228644446132, "min": 0.0627034087801197, "max": 0.07513711334182767, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27996914577784526, "min": 0.2587839719985198, "max": 0.3644865945319123, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18707115093574805, "min": 0.1599947275221804, "max": 0.3088512051777512, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7482846037429922, "min": 0.6399789100887217, "max": 1.4609578245995092, "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": 25.227272727272727, "min": 4.113636363636363, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 181.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 4.113636363636363, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 181.0, "max": 1415.0, "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": "1723559181", "python_version": "3.10.1 | packaged by conda-forge | (main, Dec 22 2021, 01:39:36) [GCC 9.4.0]", "command_line_arguments": "/home/aa/miniconda3/envs/rl-unit5/bin/mlagents-learn /home/aa/Documents/GitHub/RL-hugging_face/unit5/ml-agents/config/ppo/SnowballTarget.yaml --env=/home/aa/Documents/GitHub/RL-hugging_face/unit5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723559318" }, "total": 136.96935111284256, "count": 1, "self": 0.16697258059866726, "children": { "run_training.setup": { "total": 0.010003389092162251, "count": 1, "self": 0.010003389092162251 }, "TrainerController.start_learning": { "total": 136.79237514315173, "count": 1, "self": 0.22384484624490142, "children": { "TrainerController._reset_env": { "total": 0.8020070490892977, "count": 1, "self": 0.8020070490892977 }, "TrainerController.advance": { "total": 135.73367493785918, "count": 18204, "self": 0.0990544103551656, "children": { "env_step": { "total": 135.634620527504, "count": 18204, "self": 98.83183242729865, "children": { "SubprocessEnvManager._take_step": { "total": 36.69706802838482, "count": 18204, "self": 0.5651206823531538, "children": { "TorchPolicy.evaluate": { "total": 36.131947346031666, "count": 18204, "self": 36.131947346031666 } } }, "workers": { "total": 0.10572007182054222, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 136.5360903851688, "count": 18204, "is_parallel": true, "self": 68.73688976909034, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007940048817545176, "count": 1, "is_parallel": true, "self": 0.00021555949933826923, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005784453824162483, "count": 10, "is_parallel": true, "self": 0.0005784453824162483 } } }, "UnityEnvironment.step": { "total": 0.011895354138687253, "count": 1, "is_parallel": true, "self": 0.00016381009481847286, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00012305006384849548, "count": 1, "is_parallel": true, "self": 0.00012305006384849548 }, "communicator.exchange": { "total": 0.011143123032525182, "count": 1, "is_parallel": true, "self": 0.011143123032525182 }, "steps_from_proto": { "total": 0.0004653709474951029, "count": 1, "is_parallel": true, "self": 0.0001104818657040596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003548890817910433, "count": 10, "is_parallel": true, "self": 0.0003548890817910433 } } } } } } }, "UnityEnvironment.step": { "total": 67.79920061607845, "count": 18203, "is_parallel": true, "self": 2.7447069857735187, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3955993941053748, "count": 18203, "is_parallel": true, "self": 1.3955993941053748 }, "communicator.exchange": { "total": 55.99309195834212, "count": 18203, "is_parallel": true, "self": 55.99309195834212 }, "steps_from_proto": { "total": 7.665802277857438, "count": 18203, "is_parallel": true, "self": 1.5746500045061111, "children": { "_process_rank_one_or_two_observation": { "total": 6.091152273351327, "count": 182030, "is_parallel": true, "self": 6.091152273351327 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.225798279047012e-05, "count": 1, "self": 6.225798279047012e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 135.66116016474552, "count": 95309, "is_parallel": true, "self": 0.7164393707644194, "children": { "process_trajectory": { "total": 77.15434985957108, "count": 95309, "is_parallel": true, "self": 76.9507215586491, "children": { "RLTrainer._checkpoint": { "total": 0.20362830092199147, "count": 4, "is_parallel": true, "self": 0.20362830092199147 } } }, "_update_policy": { "total": 57.79037093441002, "count": 90, "is_parallel": true, "self": 13.943990311585367, "children": { "TorchPPOOptimizer.update": { "total": 43.846380622824654, "count": 4587, "is_parallel": true, "self": 43.846380622824654 } } } } } } } } }, "TrainerController._save_models": { "total": 0.03278605197556317, "count": 1, "self": 0.0005830279551446438, "children": { "RLTrainer._checkpoint": { "total": 0.032203024020418525, "count": 1, "self": 0.032203024020418525 } } } } } } }