{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9770574569702148, "min": 0.9770574569702148, "max": 2.872824192047119, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9328.9443359375, "min": 9328.9443359375, "max": 29420.59375, "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": 13.01370906829834, "min": 0.2637895345687866, "max": 13.01370906829834, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.67333984375, "min": 51.1751708984375, "max": 2641.5810546875, "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": 0.0719754803299735, "min": 0.0634664674901561, "max": 0.07418755202467996, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.287901921319894, "min": 0.2538658699606244, "max": 0.35691642626610987, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2016045633046066, "min": 0.1291025583963275, "max": 0.2961038468661262, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8064182532184264, "min": 0.51641023358531, "max": 1.351802888161996, "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": 25.522727272727273, "min": 3.340909090909091, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 147.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.340909090909091, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 147.0, "max": 1422.0, "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": "1674032785", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "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": "1.21.6", "end_time_seconds": "1674033225" }, "total": 439.85378525, "count": 1, "self": 0.44142473200002996, "children": { "run_training.setup": { "total": 0.11024168500000542, "count": 1, "self": 0.11024168500000542 }, "TrainerController.start_learning": { "total": 439.30211883299995, "count": 1, "self": 0.5132056940014422, "children": { "TrainerController._reset_env": { "total": 10.960610675999988, "count": 1, "self": 10.960610675999988 }, "TrainerController.advance": { "total": 427.7041054549984, "count": 18201, "self": 0.25586102300275115, "children": { "env_step": { "total": 427.44824443199565, "count": 18201, "self": 279.6346805820083, "children": { "SubprocessEnvManager._take_step": { "total": 147.54777175099224, "count": 18201, "self": 1.370160855997085, "children": { "TorchPolicy.evaluate": { "total": 146.17761089499515, "count": 18201, "self": 33.351886950003575, "children": { "TorchPolicy.sample_actions": { "total": 112.82572394499158, "count": 18201, "self": 112.82572394499158 } } } } }, "workers": { "total": 0.2657920989951208, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 438.0455140510058, "count": 18201, "is_parallel": true, "self": 210.98095238801903, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006835523999995985, "count": 1, "is_parallel": true, "self": 0.004289148999987447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025463750000085383, "count": 10, "is_parallel": true, "self": 0.0025463750000085383 } } }, "UnityEnvironment.step": { "total": 0.04491837200004056, "count": 1, "is_parallel": true, "self": 0.0005320530000290091, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003071909999903255, "count": 1, "is_parallel": true, "self": 0.0003071909999903255 }, "communicator.exchange": { "total": 0.04209343300004775, "count": 1, "is_parallel": true, "self": 0.04209343300004775 }, "steps_from_proto": { "total": 0.001985694999973475, "count": 1, "is_parallel": true, "self": 0.00046123599997827114, "children": { "_process_rank_one_or_two_observation": { "total": 0.001524458999995204, "count": 10, "is_parallel": true, "self": 0.001524458999995204 } } } } } } }, "UnityEnvironment.step": { "total": 227.06456166298676, "count": 18200, "is_parallel": true, "self": 8.486632045955787, "children": { "UnityEnvironment._generate_step_input": { "total": 4.968882612005871, "count": 18200, "is_parallel": true, "self": 4.968882612005871 }, "communicator.exchange": { "total": 179.62497701201204, "count": 18200, "is_parallel": true, "self": 179.62497701201204 }, "steps_from_proto": { "total": 33.984069993013065, "count": 18200, "is_parallel": true, "self": 7.098309037020954, "children": { "_process_rank_one_or_two_observation": { "total": 26.88576095599211, "count": 182000, "is_parallel": true, "self": 26.88576095599211 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.504400010318932e-05, "count": 1, "self": 4.504400010318932e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 424.6351472520229, "count": 350158, "is_parallel": true, "self": 9.407810944042126, "children": { "process_trajectory": { "total": 243.46165179098034, "count": 350158, "is_parallel": true, "self": 242.72556299698033, "children": { "RLTrainer._checkpoint": { "total": 0.7360887940000111, "count": 4, "is_parallel": true, "self": 0.7360887940000111 } } }, "_update_policy": { "total": 171.7656845170004, "count": 90, "is_parallel": true, "self": 44.43722670899962, "children": { "TorchPPOOptimizer.update": { "total": 127.32845780800079, "count": 4587, "is_parallel": true, "self": 127.32845780800079 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1241519640000206, "count": 1, "self": 0.00085821200002556, "children": { "RLTrainer._checkpoint": { "total": 0.12329375199999504, "count": 1, "self": 0.12329375199999504 } } } } } } }