{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8712881803512573, "min": 0.8306038975715637, "max": 2.8423805236816406, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8280.72265625, "min": 8199.21484375, "max": 29015.01953125, "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": 11.940386772155762, "min": 0.3622942268848419, "max": 11.940386772155762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2328.37548828125, "min": 70.28507995605469, "max": 2422.75830078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07077363421158939, "min": 0.06300169075656609, "max": 0.0760360257302904, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28309453684635755, "min": 0.25200676302626435, "max": 0.380180128651452, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1689763564397307, "min": 0.13392225581257805, "max": 0.2755486505726973, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6759054257589228, "min": 0.5356890232503122, "max": 1.351870420516706, "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": 23.727272727272727, "min": 3.909090909090909, "max": 23.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1044.0, "min": 172.0, "max": 1288.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.727272727272727, "min": 3.909090909090909, "max": 23.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1044.0, "min": 172.0, "max": 1288.0, "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": "1761514155", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/myenv/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": "1761514596" }, "total": 441.00486339099996, "count": 1, "self": 0.4341217879998567, "children": { "run_training.setup": { "total": 0.034909813000012946, "count": 1, "self": 0.034909813000012946 }, "TrainerController.start_learning": { "total": 440.5358317900001, "count": 1, "self": 0.37157807400171805, "children": { "TrainerController._reset_env": { "total": 3.1356666039999936, "count": 1, "self": 3.1356666039999936 }, "TrainerController.advance": { "total": 436.95290658399824, "count": 18192, "self": 0.37281585298626396, "children": { "env_step": { "total": 312.72672623499886, "count": 18192, "self": 243.37990014800687, "children": { "SubprocessEnvManager._take_step": { "total": 69.12740694199579, "count": 18192, "self": 1.2758581149834072, "children": { "TorchPolicy.evaluate": { "total": 67.85154882701238, "count": 18192, "self": 67.85154882701238 } } }, "workers": { "total": 0.21941914499620907, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 438.8292126570004, "count": 18192, "is_parallel": true, "self": 224.99405370299428, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00793119700006173, "count": 1, "is_parallel": true, "self": 0.005498823000152697, "children": { "_process_rank_one_or_two_observation": { "total": 0.002432373999909032, "count": 10, "is_parallel": true, "self": 0.002432373999909032 } } }, "UnityEnvironment.step": { "total": 0.034894364000024325, "count": 1, "is_parallel": true, "self": 0.0006171640000047773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000389161000043714, "count": 1, "is_parallel": true, "self": 0.000389161000043714 }, "communicator.exchange": { "total": 0.032000689000028615, "count": 1, "is_parallel": true, "self": 0.032000689000028615 }, "steps_from_proto": { "total": 0.0018873499999472187, "count": 1, "is_parallel": true, "self": 0.0003776140000582018, "children": { "_process_rank_one_or_two_observation": { "total": 0.001509735999889017, "count": 10, "is_parallel": true, "self": 0.001509735999889017 } } } } } } }, "UnityEnvironment.step": { "total": 213.83515895400615, "count": 18191, "is_parallel": true, "self": 10.194048059010925, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4721867610045365, "count": 18191, "is_parallel": true, "self": 5.4721867610045365 }, "communicator.exchange": { "total": 162.40978425098945, "count": 18191, "is_parallel": true, "self": 162.40978425098945 }, "steps_from_proto": { "total": 35.75913988300124, "count": 18191, "is_parallel": true, "self": 6.85826327401503, "children": { "_process_rank_one_or_two_observation": { "total": 28.90087660898621, "count": 181910, "is_parallel": true, "self": 28.90087660898621 } } } } } } } } } } }, "trainer_advance": { "total": 123.85336449601311, "count": 18192, "self": 0.43180732501014063, "children": { "process_trajectory": { "total": 27.05016987900376, "count": 18192, "self": 26.61952265400373, "children": { "RLTrainer._checkpoint": { "total": 0.4306472250000297, "count": 4, "self": 0.4306472250000297 } } }, "_update_policy": { "total": 96.37138729199921, "count": 90, "self": 41.589312989004156, "children": { "TorchPPOOptimizer.update": { "total": 54.782074302995056, "count": 4587, "self": 54.782074302995056 } } } } } } }, "trainer_threads": { "total": 8.660000503368792e-07, "count": 1, "self": 8.660000503368792e-07 }, "TrainerController._save_models": { "total": 0.07567966200008414, "count": 1, "self": 0.0006981730001598407, "children": { "RLTrainer._checkpoint": { "total": 0.0749814889999243, "count": 1, "self": 0.0749814889999243 } } } } } } }