{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9571311473846436, "min": 0.9571311473846436, "max": 2.799241304397583, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9096.57421875, "min": 9096.57421875, "max": 28574.654296875, "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": 12.944393157958984, "min": 0.44061967730522156, "max": 12.944393157958984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.15673828125, "min": 85.48021697998047, "max": 2595.271484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0673171342841313, "min": 0.061649093103387356, "max": 0.07881013248498123, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2692685371365252, "min": 0.24659637241354943, "max": 0.3716557517050829, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20633791591606887, "min": 0.14275723047024916, "max": 0.292900220728388, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8253516636642755, "min": 0.5710289218809966, "max": 1.3662757446952893, "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": 25.65909090909091, "min": 4.0227272727272725, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 177.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 4.0227272727272725, "max": 25.65909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 177.0, "max": 1404.0, "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": "1731954797", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731955233" }, "total": 435.10527656700003, "count": 1, "self": 0.47540455300008944, "children": { "run_training.setup": { "total": 0.05586317500001314, "count": 1, "self": 0.05586317500001314 }, "TrainerController.start_learning": { "total": 434.57400883899993, "count": 1, "self": 0.3657741399933343, "children": { "TrainerController._reset_env": { "total": 5.243837821999989, "count": 1, "self": 5.243837821999989 }, "TrainerController.advance": { "total": 428.8793391440066, "count": 18192, "self": 0.3752344170040942, "children": { "env_step": { "total": 301.3446995929982, "count": 18192, "self": 229.43320615399608, "children": { "SubprocessEnvManager._take_step": { "total": 71.68740222301011, "count": 18192, "self": 1.2508810070098662, "children": { "TorchPolicy.evaluate": { "total": 70.43652121600024, "count": 18192, "self": 70.43652121600024 } } }, "workers": { "total": 0.22409121599201853, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 433.143583814001, "count": 18192, "is_parallel": true, "self": 232.57925414400535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002448741999955928, "count": 1, "is_parallel": true, "self": 0.000725587999909294, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017231540000466339, "count": 10, "is_parallel": true, "self": 0.0017231540000466339 } } }, "UnityEnvironment.step": { "total": 0.0729756349999775, "count": 1, "is_parallel": true, "self": 0.00073410599992485, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041636200000993995, "count": 1, "is_parallel": true, "self": 0.00041636200000993995 }, "communicator.exchange": { "total": 0.06965304499999547, "count": 1, "is_parallel": true, "self": 0.06965304499999547 }, "steps_from_proto": { "total": 0.0021721220000472385, "count": 1, "is_parallel": true, "self": 0.0004553429999987202, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017167790000485184, "count": 10, "is_parallel": true, "self": 0.0017167790000485184 } } } } } } }, "UnityEnvironment.step": { "total": 200.56432966999563, "count": 18191, "is_parallel": true, "self": 9.924352746004786, "children": { "UnityEnvironment._generate_step_input": { "total": 5.459999988000163, "count": 18191, "is_parallel": true, "self": 5.459999988000163 }, "communicator.exchange": { "total": 153.36842940099677, "count": 18191, "is_parallel": true, "self": 153.36842940099677 }, "steps_from_proto": { "total": 31.811547534993906, "count": 18191, "is_parallel": true, "self": 5.7705593929903785, "children": { "_process_rank_one_or_two_observation": { "total": 26.040988142003528, "count": 181910, "is_parallel": true, "self": 26.040988142003528 } } } } } } } } } } }, "trainer_advance": { "total": 127.15940513400432, "count": 18192, "self": 0.44396313200610393, "children": { "process_trajectory": { "total": 28.284206971997833, "count": 18192, "self": 27.74028909099792, "children": { "RLTrainer._checkpoint": { "total": 0.5439178809999135, "count": 4, "self": 0.5439178809999135 } } }, "_update_policy": { "total": 98.43123503000038, "count": 90, "self": 41.50979817000183, "children": { "TorchPPOOptimizer.update": { "total": 56.92143685999855, "count": 4587, "self": 56.92143685999855 } } } } } } }, "trainer_threads": { "total": 1.3760000001639128e-06, "count": 1, "self": 1.3760000001639128e-06 }, "TrainerController._save_models": { "total": 0.08505635699998493, "count": 1, "self": 0.0008614570000418098, "children": { "RLTrainer._checkpoint": { "total": 0.08419489999994312, "count": 1, "self": 0.08419489999994312 } } } } } } }