{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8999366164207458, "min": 0.8955281376838684, "max": 2.8606204986572266, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8582.6953125, "min": 8582.6953125, "max": 29295.615234375, "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": 12.796937942504883, "min": 0.3882239758968353, "max": 12.796937942504883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.40283203125, "min": 75.3154525756836, "max": 2575.33984375, "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": 0.07186025705225035, "min": 0.06512115761100122, "max": 0.07480964504294188, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2874410282090014, "min": 0.2604846304440049, "max": 0.3664452390443972, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1782816089324507, "min": 0.10486233068228352, "max": 0.2782416669469253, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7131264357298028, "min": 0.4194493227291341, "max": 1.364502027046447, "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": 25.25, "min": 3.159090909090909, "max": 25.30909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 139.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.159090909090909, "max": 25.30909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 139.0, "max": 1392.0, "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": "1707423720", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707424175" }, "total": 454.369172543, "count": 1, "self": 0.48935827599996173, "children": { "run_training.setup": { "total": 0.051626925000050505, "count": 1, "self": 0.051626925000050505 }, "TrainerController.start_learning": { "total": 453.828187342, "count": 1, "self": 0.6009790989971862, "children": { "TrainerController._reset_env": { "total": 3.1410442670000975, "count": 1, "self": 3.1410442670000975 }, "TrainerController.advance": { "total": 449.9846126150027, "count": 18198, "self": 0.2882123100048375, "children": { "env_step": { "total": 449.69640030499784, "count": 18198, "self": 293.17944429299143, "children": { "SubprocessEnvManager._take_step": { "total": 156.2225049420058, "count": 18198, "self": 1.5135084710017281, "children": { "TorchPolicy.evaluate": { "total": 154.70899647100407, "count": 18198, "self": 154.70899647100407 } } }, "workers": { "total": 0.2944510700006049, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 452.66735119899886, "count": 18198, "is_parallel": true, "self": 222.05339057899607, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004615104999970754, "count": 1, "is_parallel": true, "self": 0.0031031669999492806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015119380000214733, "count": 10, "is_parallel": true, "self": 0.0015119380000214733 } } }, "UnityEnvironment.step": { "total": 0.03644427999995514, "count": 1, "is_parallel": true, "self": 0.0006795880000254328, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040760499996395083, "count": 1, "is_parallel": true, "self": 0.00040760499996395083 }, "communicator.exchange": { "total": 0.0334286099999872, "count": 1, "is_parallel": true, "self": 0.0334286099999872 }, "steps_from_proto": { "total": 0.0019284769999785567, "count": 1, "is_parallel": true, "self": 0.0004478540000718567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014806229999067, "count": 10, "is_parallel": true, "self": 0.0014806229999067 } } } } } } }, "UnityEnvironment.step": { "total": 230.61396062000279, "count": 18197, "is_parallel": true, "self": 10.950074330001712, "children": { "UnityEnvironment._generate_step_input": { "total": 5.631455779991597, "count": 18197, "is_parallel": true, "self": 5.631455779991597 }, "communicator.exchange": { "total": 179.64325763401098, "count": 18197, "is_parallel": true, "self": 179.64325763401098 }, "steps_from_proto": { "total": 34.3891728759985, "count": 18197, "is_parallel": true, "self": 6.4437020619895975, "children": { "_process_rank_one_or_two_observation": { "total": 27.9454708140089, "count": 181970, "is_parallel": true, "self": 27.9454708140089 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001334160000396878, "count": 1, "self": 0.0001334160000396878, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 444.4794351159718, "count": 688989, "is_parallel": true, "self": 14.365254949047994, "children": { "process_trajectory": { "total": 244.91611393592427, "count": 688989, "is_parallel": true, "self": 244.14556938292412, "children": { "RLTrainer._checkpoint": { "total": 0.7705445530001498, "count": 4, "is_parallel": true, "self": 0.7705445530001498 } } }, "_update_policy": { "total": 185.19806623099953, "count": 90, "is_parallel": true, "self": 52.98430208499269, "children": { "TorchPPOOptimizer.update": { "total": 132.21376414600684, "count": 4587, "is_parallel": true, "self": 132.21376414600684 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10141794499998014, "count": 1, "self": 0.0011104589999604286, "children": { "RLTrainer._checkpoint": { "total": 0.10030748600001971, "count": 1, "self": 0.10030748600001971 } } } } } } }