{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.671748697757721, "min": 0.671748697757721, "max": 2.8592498302459717, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6384.2998046875, "min": 6384.2998046875, "max": 29187.22265625, "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": 12.624820709228516, "min": 0.3231083154678345, "max": 12.624820709228516, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.840087890625, "min": 62.683013916015625, "max": 2544.546142578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06694130706227061, "min": 0.06237879227627156, "max": 0.08129142236030734, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26776522824908244, "min": 0.2531023575426718, "max": 0.37434323039134126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1928187821279554, "min": 0.0845255592961193, "max": 0.2956271731824267, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7712751285118216, "min": 0.3381022371844772, "max": 1.3167834650067722, "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": 25.363636363636363, "min": 2.5, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 110.0, "max": 1362.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 2.5, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 110.0, "max": 1362.0, "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": "1754171722", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754172152" }, "total": 430.445719725, "count": 1, "self": 0.438210303000119, "children": { "run_training.setup": { "total": 0.022631209999985913, "count": 1, "self": 0.022631209999985913 }, "TrainerController.start_learning": { "total": 429.9848782119999, "count": 1, "self": 0.3551973289874013, "children": { "TrainerController._reset_env": { "total": 3.5041262439999628, "count": 1, "self": 3.5041262439999628 }, "TrainerController.advance": { "total": 426.0447061210125, "count": 18192, "self": 0.373027962014703, "children": { "env_step": { "total": 306.767292129001, "count": 18192, "self": 235.87200322100057, "children": { "SubprocessEnvManager._take_step": { "total": 70.68249487099263, "count": 18192, "self": 1.26904893098731, "children": { "TorchPolicy.evaluate": { "total": 69.41344594000532, "count": 18192, "self": 69.41344594000532 } } }, "workers": { "total": 0.21279403700782495, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 428.5711332300018, "count": 18192, "is_parallel": true, "self": 221.61723398300535, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005888068999979623, "count": 1, "is_parallel": true, "self": 0.004007896999951299, "children": { "_process_rank_one_or_two_observation": { "total": 0.001880172000028324, "count": 10, "is_parallel": true, "self": 0.001880172000028324 } } }, "UnityEnvironment.step": { "total": 0.035050022999939756, "count": 1, "is_parallel": true, "self": 0.0005989479998333991, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004427910000686097, "count": 1, "is_parallel": true, "self": 0.0004427910000686097 }, "communicator.exchange": { "total": 0.03221514200004094, "count": 1, "is_parallel": true, "self": 0.03221514200004094 }, "steps_from_proto": { "total": 0.0017931419999968057, "count": 1, "is_parallel": true, "self": 0.0003431559997579825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014499860002388232, "count": 10, "is_parallel": true, "self": 0.0014499860002388232 } } } } } } }, "UnityEnvironment.step": { "total": 206.95389924699646, "count": 18191, "is_parallel": true, "self": 9.86860691599702, "children": { "UnityEnvironment._generate_step_input": { "total": 5.541072724999367, "count": 18191, "is_parallel": true, "self": 5.541072724999367 }, "communicator.exchange": { "total": 158.82160301699287, "count": 18191, "is_parallel": true, "self": 158.82160301699287 }, "steps_from_proto": { "total": 32.7226165890072, "count": 18191, "is_parallel": true, "self": 5.880591099994604, "children": { "_process_rank_one_or_two_observation": { "total": 26.8420254890126, "count": 181910, "is_parallel": true, "self": 26.8420254890126 } } } } } } } } } } }, "trainer_advance": { "total": 118.90438602999677, "count": 18192, "self": 0.4345352240060265, "children": { "process_trajectory": { "total": 26.600431898990564, "count": 18192, "self": 26.14630227199052, "children": { "RLTrainer._checkpoint": { "total": 0.454129627000043, "count": 4, "self": 0.454129627000043 } } }, "_update_policy": { "total": 91.86941890700018, "count": 90, "self": 37.93004083599999, "children": { "TorchPPOOptimizer.update": { "total": 53.93937807100019, "count": 4587, "self": 53.93937807100019 } } } } } } }, "trainer_threads": { "total": 8.279999974547536e-07, "count": 1, "self": 8.279999974547536e-07 }, "TrainerController._save_models": { "total": 0.08084769000004144, "count": 1, "self": 0.0008111590000225988, "children": { "RLTrainer._checkpoint": { "total": 0.08003653100001884, "count": 1, "self": 0.08003653100001884 } } } } } } }