{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.905778169631958, "min": 0.905778169631958, "max": 2.8685221672058105, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8608.515625, "min": 8608.515625, "max": 29281.875, "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": 12.80480670928955, "min": 0.5286368727684021, "max": 12.80480670928955, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.937255859375, "min": 102.55555725097656, "max": 2591.746826171875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07112748517857992, "min": 0.060467283619943246, "max": 0.07602422324486599, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2845099407143197, "min": 0.24186913447977298, "max": 0.38012111622433, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20664830874724716, "min": 0.11357280076253137, "max": 0.30434882772319455, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8265932349889886, "min": 0.4542912030501255, "max": 1.2731424082143636, "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.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.Environment.CumulativeReward.mean": { "value": 25.386363636363637, "min": 3.409090909090909, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 150.0, "max": 1383.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.409090909090909, "max": 25.386363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 150.0, "max": 1383.0, "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": "1774179029", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1774179465" }, "total": 435.7156982719998, "count": 1, "self": 0.43125111200015454, "children": { "run_training.setup": { "total": 0.036543625999911455, "count": 1, "self": 0.036543625999911455 }, "TrainerController.start_learning": { "total": 435.24790353399976, "count": 1, "self": 0.34648210699151605, "children": { "TrainerController._reset_env": { "total": 2.820006397999805, "count": 1, "self": 2.820006397999805 }, "TrainerController.advance": { "total": 432.00433644400846, "count": 18192, "self": 0.36170796697797414, "children": { "env_step": { "total": 313.0784550950293, "count": 18192, "self": 244.66364245306613, "children": { "SubprocessEnvManager._take_step": { "total": 68.20899246596127, "count": 18192, "self": 1.2408510189502522, "children": { "TorchPolicy.evaluate": { "total": 66.96814144701102, "count": 18192, "self": 66.96814144701102 } } }, "workers": { "total": 0.20582017600190738, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 433.31958724700917, "count": 18192, "is_parallel": true, "self": 217.89333649698347, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004727820999960386, "count": 1, "is_parallel": true, "self": 0.0032780980004645244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014497229994958616, "count": 10, "is_parallel": true, "self": 0.0014497229994958616 } } }, "UnityEnvironment.step": { "total": 0.03888216799987276, "count": 1, "is_parallel": true, "self": 0.0006053570000403852, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042037599996547215, "count": 1, "is_parallel": true, "self": 0.00042037599996547215 }, "communicator.exchange": { "total": 0.03602811600012501, "count": 1, "is_parallel": true, "self": 0.03602811600012501 }, "steps_from_proto": { "total": 0.0018283189997418958, "count": 1, "is_parallel": true, "self": 0.00035576300069806166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014725559990438342, "count": 10, "is_parallel": true, "self": 0.0014725559990438342 } } } } } } }, "UnityEnvironment.step": { "total": 215.4262507500257, "count": 18191, "is_parallel": true, "self": 10.286056151973298, "children": { "UnityEnvironment._generate_step_input": { "total": 5.822702507019585, "count": 18191, "is_parallel": true, "self": 5.822702507019585 }, "communicator.exchange": { "total": 163.0036749080332, "count": 18191, "is_parallel": true, "self": 163.0036749080332 }, "steps_from_proto": { "total": 36.31381718299963, "count": 18191, "is_parallel": true, "self": 6.428278852933545, "children": { "_process_rank_one_or_two_observation": { "total": 29.885538330066083, "count": 181910, "is_parallel": true, "self": 29.885538330066083 } } } } } } } } } } }, "trainer_advance": { "total": 118.56417338200117, "count": 18192, "self": 0.4088254809657883, "children": { "process_trajectory": { "total": 26.314765953033202, "count": 18192, "self": 25.919800649033277, "children": { "RLTrainer._checkpoint": { "total": 0.3949653039999248, "count": 4, "self": 0.3949653039999248 } } }, "_update_policy": { "total": 91.84058194800218, "count": 90, "self": 37.34156405700105, "children": { "TorchPPOOptimizer.update": { "total": 54.49901789100113, "count": 4587, "self": 54.49901789100113 } } } } } } }, "trainer_threads": { "total": 1.0090002433571499e-06, "count": 1, "self": 1.0090002433571499e-06 }, "TrainerController._save_models": { "total": 0.07707757599973775, "count": 1, "self": 0.0007462879998456629, "children": { "RLTrainer._checkpoint": { "total": 0.07633128799989208, "count": 1, "self": 0.07633128799989208 } } } } } } }