{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0848110914230347, "min": 1.076097011566162, "max": 2.86898136138916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10405.5078125, "min": 10405.5078125, "max": 29412.796875, "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": 12.89698314666748, "min": 0.3579121232032776, "max": 12.89698314666748, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2514.91162109375, "min": 69.43495178222656, "max": 2615.5498046875, "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": 0.06405190186706022, "min": 0.06082926010461889, "max": 0.07328092960589999, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2562076074682409, "min": 0.24331704041847557, "max": 0.35921890463899164, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19845505124505827, "min": 0.11366206472830884, "max": 0.2798831372868781, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7938202049802331, "min": 0.45464825891323535, "max": 1.3994156864343905, "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": 25.727272727272727, "min": 3.2045454545454546, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 141.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 3.2045454545454546, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 141.0, "max": 1411.0, "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": "1690473496", "python_version": "3.8.16 (default, Jun 12 2023, 18:09:05) \n[GCC 11.2.0]", "command_line_arguments": "/global/home/users/lizhen/scratch/miniconda3/envs/huggingface/bin/mlagents-learn content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690474160" }, "total": 664.0483916400117, "count": 1, "self": 0.6383521260286216, "children": { "run_training.setup": { "total": 0.13603596299071796, "count": 1, "self": 0.13603596299071796 }, "TrainerController.start_learning": { "total": 663.2740035509923, "count": 1, "self": 0.5275094436074141, "children": { "TrainerController._reset_env": { "total": 19.82807365601184, "count": 1, "self": 19.82807365601184 }, "TrainerController.advance": { "total": 642.7602568503644, "count": 18207, "self": 0.24143577128415927, "children": { "env_step": { "total": 642.5188210790802, "count": 18207, "self": 518.8149093606335, "children": { "SubprocessEnvManager._take_step": { "total": 123.44737944906228, "count": 18207, "self": 1.7346869605244137, "children": { "TorchPolicy.evaluate": { "total": 121.71269248853787, "count": 18207, "self": 121.71269248853787 } } }, "workers": { "total": 0.25653226938447915, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 661.8958046842308, "count": 18207, "is_parallel": true, "self": 253.6707756453543, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006111263995990157, "count": 1, "is_parallel": true, "self": 0.001358259964035824, "children": { "_process_rank_one_or_two_observation": { "total": 0.004753004031954333, "count": 10, "is_parallel": true, "self": 0.004753004031954333 } } }, "UnityEnvironment.step": { "total": 0.05519329500384629, "count": 1, "is_parallel": true, "self": 0.0011531900090631098, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008687630179338157, "count": 1, "is_parallel": true, "self": 0.0008687630179338157 }, "communicator.exchange": { "total": 0.04929768099100329, "count": 1, "is_parallel": true, "self": 0.04929768099100329 }, "steps_from_proto": { "total": 0.0038736609858460724, "count": 1, "is_parallel": true, "self": 0.0007949860009830445, "children": { "_process_rank_one_or_two_observation": { "total": 0.003078674984863028, "count": 10, "is_parallel": true, "self": 0.003078674984863028 } } } } } } }, "UnityEnvironment.step": { "total": 408.2250290388765, "count": 18206, "is_parallel": true, "self": 18.247259002324427, "children": { "UnityEnvironment._generate_step_input": { "total": 9.646688927372452, "count": 18206, "is_parallel": true, "self": 9.646688927372452 }, "communicator.exchange": { "total": 327.51333426719066, "count": 18206, "is_parallel": true, "self": 327.51333426719066 }, "steps_from_proto": { "total": 52.81774684198899, "count": 18206, "is_parallel": true, "self": 10.37843413525843, "children": { "_process_rank_one_or_two_observation": { "total": 42.43931270673056, "count": 182060, "is_parallel": true, "self": 42.43931270673056 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001809920067898929, "count": 1, "self": 0.0001809920067898929, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 637.2037052743835, "count": 597991, "is_parallel": true, "self": 15.018656438507605, "children": { "process_trajectory": { "total": 360.1638104477606, "count": 597991, "is_parallel": true, "self": 358.2469938157592, "children": { "RLTrainer._checkpoint": { "total": 1.916816632001428, "count": 4, "is_parallel": true, "self": 1.916816632001428 } } }, "_update_policy": { "total": 262.0212383881153, "count": 90, "is_parallel": true, "self": 43.925837532413425, "children": { "TorchPPOOptimizer.update": { "total": 218.09540085570188, "count": 4587, "is_parallel": true, "self": 218.09540085570188 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15798260900191963, "count": 1, "self": 0.010100003011757508, "children": { "RLTrainer._checkpoint": { "total": 0.14788260599016212, "count": 1, "self": 0.14788260599016212 } } } } } } }