{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9396819472312927, "min": 0.9396819472312927, "max": 2.8167660236358643, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8930.7373046875, "min": 8930.7373046875, "max": 28753.546875, "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": 13.134748458862305, "min": 0.44492340087890625, "max": 13.134748458862305, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2561.27587890625, "min": 86.31513977050781, "max": 2668.38427734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0673201327354036, "min": 0.06529412323447212, "max": 0.07194760295315063, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2692805309416144, "min": 0.26117649293788847, "max": 0.3543244266690796, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19299874462406424, "min": 0.11606358234472709, "max": 0.3058497264630654, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.771994978496257, "min": 0.46425432937890837, "max": 1.5292486323153271, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.0013851600382799997, "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": 0.9617200000000001, "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": 25.772727272727273, "min": 3.8181818181818183, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 168.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 3.8181818181818183, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 168.0, "max": 1408.0, "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": "1735146139", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume", "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": "1735146790" }, "total": 650.9724590690003, "count": 1, "self": 0.42990957199981494, "children": { "run_training.setup": { "total": 0.055157618000521325, "count": 1, "self": 0.055157618000521325 }, "TrainerController.start_learning": { "total": 650.4873918789999, "count": 1, "self": 0.3939848499949221, "children": { "TrainerController._reset_env": { "total": 2.022015487000317, "count": 1, "self": 2.022015487000317 }, "TrainerController.advance": { "total": 647.9862215940047, "count": 18192, "self": 0.39206350915901567, "children": { "env_step": { "total": 312.6104515338666, "count": 18192, "self": 237.80901234792327, "children": { "SubprocessEnvManager._take_step": { "total": 74.57440797300842, "count": 18192, "self": 1.3408157321109684, "children": { "TorchPolicy.evaluate": { "total": 73.23359224089745, "count": 18192, "self": 73.23359224089745 } } }, "workers": { "total": 0.22703121293488948, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 649.0796868350244, "count": 18192, "is_parallel": true, "self": 441.5061349939897, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023508989997935714, "count": 1, "is_parallel": true, "self": 0.0006634860001213383, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016874129996722331, "count": 10, "is_parallel": true, "self": 0.0016874129996722331 } } }, "UnityEnvironment.step": { "total": 0.03630692299975635, "count": 1, "is_parallel": true, "self": 0.0007421489999615005, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004338589997132658, "count": 1, "is_parallel": true, "self": 0.0004338589997132658 }, "communicator.exchange": { "total": 0.03245129700007965, "count": 1, "is_parallel": true, "self": 0.03245129700007965 }, "steps_from_proto": { "total": 0.0026796180000019376, "count": 1, "is_parallel": true, "self": 0.0006261410017032176, "children": { "_process_rank_one_or_two_observation": { "total": 0.00205347699829872, "count": 10, "is_parallel": true, "self": 0.00205347699829872 } } } } } } }, "UnityEnvironment.step": { "total": 207.5735518410347, "count": 18191, "is_parallel": true, "self": 9.950755628023217, "children": { "UnityEnvironment._generate_step_input": { "total": 5.550318622996201, "count": 18191, "is_parallel": true, "self": 5.550318622996201 }, "communicator.exchange": { "total": 159.04938967006092, "count": 18191, "is_parallel": true, "self": 159.04938967006092 }, "steps_from_proto": { "total": 33.02308791995438, "count": 18191, "is_parallel": true, "self": 5.994790194120469, "children": { "_process_rank_one_or_two_observation": { "total": 27.02829772583391, "count": 181910, "is_parallel": true, "self": 27.02829772583391 } } } } } } } } } } }, "trainer_advance": { "total": 334.98370655097915, "count": 18192, "self": 0.45756635600537265, "children": { "process_trajectory": { "total": 29.570431391973216, "count": 18192, "self": 29.18534626597193, "children": { "RLTrainer._checkpoint": { "total": 0.38508512600128597, "count": 4, "self": 0.38508512600128597 } } }, "_update_policy": { "total": 304.95570880300056, "count": 90, "self": 123.13914425996973, "children": { "TorchPPOOptimizer.update": { "total": 181.81656454303084, "count": 15290, "self": 181.81656454303084 } } } } } } }, "trainer_threads": { "total": 1.3700000636163168e-06, "count": 1, "self": 1.3700000636163168e-06 }, "TrainerController._save_models": { "total": 0.0851685779998661, "count": 1, "self": 0.0011245789992244681, "children": { "RLTrainer._checkpoint": { "total": 0.08404399900064163, "count": 1, "self": 0.08404399900064163 } } } } } } }