{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8307197093963623, "min": 0.814931333065033, "max": 2.823295831680298, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7895.16015625, "min": 7895.16015625, "max": 28820.203125, "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": 13.043122291564941, "min": 0.5503689646720886, "max": 13.05781364440918, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2543.408935546875, "min": 106.77157592773438, "max": 2663.7939453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06972542928433897, "min": 0.06320361745629806, "max": 0.07583091872557085, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2789017171373559, "min": 0.25281446982519223, "max": 0.37915459362785425, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20867198683759744, "min": 0.13124495414747656, "max": 0.31140150137099565, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8346879473503898, "min": 0.5249798165899062, "max": 1.4049589803405835, "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": 25.40909090909091, "min": 4.2272727272727275, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 186.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 4.2272727272727275, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 186.0, "max": 1422.0, "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": "1739772423", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739772898" }, "total": 475.4302374519999, "count": 1, "self": 0.5449136209999779, "children": { "run_training.setup": { "total": 0.024781132999919464, "count": 1, "self": 0.024781132999919464 }, "TrainerController.start_learning": { "total": 474.860542698, "count": 1, "self": 0.4916823170038924, "children": { "TrainerController._reset_env": { "total": 2.4883565830000407, "count": 1, "self": 2.4883565830000407 }, "TrainerController.advance": { "total": 471.7985964089959, "count": 18192, "self": 0.4718278270097471, "children": { "env_step": { "total": 327.4689838629855, "count": 18192, "self": 281.9976978300107, "children": { "SubprocessEnvManager._take_step": { "total": 45.182524544977696, "count": 18192, "self": 1.441254906957397, "children": { "TorchPolicy.evaluate": { "total": 43.7412696380203, "count": 18192, "self": 43.7412696380203 } } }, "workers": { "total": 0.2887614879971352, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 473.20266036801036, "count": 18192, "is_parallel": true, "self": 226.40797978103717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00430350500005261, "count": 1, "is_parallel": true, "self": 0.0025270739998859426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017764310001666672, "count": 10, "is_parallel": true, "self": 0.0017764310001666672 } } }, "UnityEnvironment.step": { "total": 0.043307638999976916, "count": 1, "is_parallel": true, "self": 0.00070600200001536, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004630109999652632, "count": 1, "is_parallel": true, "self": 0.0004630109999652632 }, "communicator.exchange": { "total": 0.03969027100004041, "count": 1, "is_parallel": true, "self": 0.03969027100004041 }, "steps_from_proto": { "total": 0.002448354999955882, "count": 1, "is_parallel": true, "self": 0.00042988199982119113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020184730001346907, "count": 10, "is_parallel": true, "self": 0.0020184730001346907 } } } } } } }, "UnityEnvironment.step": { "total": 246.7946805869732, "count": 18191, "is_parallel": true, "self": 11.93815179896319, "children": { "UnityEnvironment._generate_step_input": { "total": 6.473079466014042, "count": 18191, "is_parallel": true, "self": 6.473079466014042 }, "communicator.exchange": { "total": 190.81247506699629, "count": 18191, "is_parallel": true, "self": 190.81247506699629 }, "steps_from_proto": { "total": 37.57097425499967, "count": 18191, "is_parallel": true, "self": 7.06015867405074, "children": { "_process_rank_one_or_two_observation": { "total": 30.51081558094893, "count": 181910, "is_parallel": true, "self": 30.51081558094893 } } } } } } } } } } }, "trainer_advance": { "total": 143.85778471900062, "count": 18192, "self": 0.6267137019960956, "children": { "process_trajectory": { "total": 26.66479107500436, "count": 18192, "self": 26.263030715004334, "children": { "RLTrainer._checkpoint": { "total": 0.4017603600000257, "count": 4, "self": 0.4017603600000257 } } }, "_update_policy": { "total": 116.56627994200016, "count": 90, "self": 46.572380709997105, "children": { "TorchPPOOptimizer.update": { "total": 69.99389923200306, "count": 4587, "self": 69.99389923200306 } } } } } } }, "trainer_threads": { "total": 1.0310000106983352e-06, "count": 1, "self": 1.0310000106983352e-06 }, "TrainerController._save_models": { "total": 0.08190635800019663, "count": 1, "self": 0.0010967400000936323, "children": { "RLTrainer._checkpoint": { "total": 0.080809618000103, "count": 1, "self": 0.080809618000103 } } } } } } }