{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.987085223197937, "min": 0.987085223197937, "max": 2.865779161453247, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9424.689453125, "min": 9424.689453125, "max": 29379.96875, "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": 13.047520637512207, "min": 0.24890051782131195, "max": 13.047520637512207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2544.2666015625, "min": 48.28670120239258, "max": 2660.69091796875, "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": 0.06879988761776237, "min": 0.06220617150373109, "max": 0.07669082522944674, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2751995504710495, "min": 0.2523718906644111, "max": 0.38345412614723373, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1965781988612577, "min": 0.12908176673169924, "max": 0.2890759396202424, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7863127954450309, "min": 0.516327066926797, "max": 1.4453796981012121, "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": 25.772727272727273, "min": 3.7045454545454546, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 163.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.7045454545454546, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 163.0, "max": 1405.0, "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": "1710937259", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710937690" }, "total": 431.3706406639999, "count": 1, "self": 0.4398539289998098, "children": { "run_training.setup": { "total": 0.0534860990001107, "count": 1, "self": 0.0534860990001107 }, "TrainerController.start_learning": { "total": 430.877300636, "count": 1, "self": 0.5513613909895412, "children": { "TrainerController._reset_env": { "total": 3.194324938000136, "count": 1, "self": 3.194324938000136 }, "TrainerController.advance": { "total": 427.03816716201027, "count": 18199, "self": 0.25173599702839056, "children": { "env_step": { "total": 426.7864311649819, "count": 18199, "self": 273.3354279479879, "children": { "SubprocessEnvManager._take_step": { "total": 153.18086734198891, "count": 18199, "self": 1.3928590799805534, "children": { "TorchPolicy.evaluate": { "total": 151.78800826200836, "count": 18199, "self": 151.78800826200836 } } }, "workers": { "total": 0.2701358750050531, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 429.7886573049991, "count": 18199, "is_parallel": true, "self": 217.07156845799705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008539076000033674, "count": 1, "is_parallel": true, "self": 0.003767150999919977, "children": { "_process_rank_one_or_two_observation": { "total": 0.004771925000113697, "count": 10, "is_parallel": true, "self": 0.004771925000113697 } } }, "UnityEnvironment.step": { "total": 0.07035331500014763, "count": 1, "is_parallel": true, "self": 0.0006802100001550571, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003981190000104107, "count": 1, "is_parallel": true, "self": 0.0003981190000104107 }, "communicator.exchange": { "total": 0.06724314500002038, "count": 1, "is_parallel": true, "self": 0.06724314500002038 }, "steps_from_proto": { "total": 0.002031840999961787, "count": 1, "is_parallel": true, "self": 0.0003965559999414836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016352850000203034, "count": 10, "is_parallel": true, "self": 0.0016352850000203034 } } } } } } }, "UnityEnvironment.step": { "total": 212.71708884700206, "count": 18198, "is_parallel": true, "self": 9.921376013066265, "children": { "UnityEnvironment._generate_step_input": { "total": 5.219845875980354, "count": 18198, "is_parallel": true, "self": 5.219845875980354 }, "communicator.exchange": { "total": 164.84809571997926, "count": 18198, "is_parallel": true, "self": 164.84809571997926 }, "steps_from_proto": { "total": 32.727771237976185, "count": 18198, "is_parallel": true, "self": 6.029761086941107, "children": { "_process_rank_one_or_two_observation": { "total": 26.698010151035078, "count": 181980, "is_parallel": true, "self": 26.698010151035078 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00032180399989556463, "count": 1, "self": 0.00032180399989556463, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 421.64332100305114, "count": 661491, "is_parallel": true, "self": 14.08230371319928, "children": { "process_trajectory": { "total": 231.83418663985185, "count": 661491, "is_parallel": true, "self": 231.25814347585197, "children": { "RLTrainer._checkpoint": { "total": 0.5760431639998842, "count": 4, "is_parallel": true, "self": 0.5760431639998842 } } }, "_update_policy": { "total": 175.72683065, "count": 90, "is_parallel": true, "self": 49.28164677900759, "children": { "TorchPPOOptimizer.update": { "total": 126.44518387099242, "count": 4587, "is_parallel": true, "self": 126.44518387099242 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09312534100013181, "count": 1, "self": 0.001015263000226696, "children": { "RLTrainer._checkpoint": { "total": 0.09211007799990512, "count": 1, "self": 0.09211007799990512 } } } } } } }