{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9133936762809753, "min": 0.9133936762809753, "max": 2.879502534866333, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8680.8935546875, "min": 8680.8935546875, "max": 29393.962890625, "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": 12.443099021911621, "min": 0.46676257252693176, "max": 12.443099021911621, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2426.404296875, "min": 90.55194091796875, "max": 2507.48779296875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.066661940322471, "min": 0.06392240664561041, "max": 0.07602945301286858, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.266647761289884, "min": 0.2617452530690107, "max": 0.3801472650643429, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2071432456666348, "min": 0.10288163358984771, "max": 0.29552779178701194, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8285729826665392, "min": 0.41152653435939085, "max": 1.4634633426572763, "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": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.3999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "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": 24.886363636363637, "min": 2.8863636363636362, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1095.0, "min": 127.0, "max": 1366.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.886363636363637, "min": 2.8863636363636362, "max": 24.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1095.0, "min": 127.0, "max": 1366.0, "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": "1745491733", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745492160" }, "total": 426.77446818199985, "count": 1, "self": 0.4382948539998779, "children": { "run_training.setup": { "total": 0.030650683999965622, "count": 1, "self": 0.030650683999965622 }, "TrainerController.start_learning": { "total": 426.305522644, "count": 1, "self": 0.34828151900001103, "children": { "TrainerController._reset_env": { "total": 3.1168185569999878, "count": 1, "self": 3.1168185569999878 }, "TrainerController.advance": { "total": 422.7575020080002, "count": 18192, "self": 0.37912960800531437, "children": { "env_step": { "total": 299.7707756819931, "count": 18192, "self": 228.09861133396964, "children": { "SubprocessEnvManager._take_step": { "total": 71.4646508600124, "count": 18192, "self": 1.2644228280170182, "children": { "TorchPolicy.evaluate": { "total": 70.20022803199538, "count": 18192, "self": 70.20022803199538 } } }, "workers": { "total": 0.2075134880110454, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 424.7603650919973, "count": 18192, "is_parallel": true, "self": 225.08678720399882, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007184316000007129, "count": 1, "is_parallel": true, "self": 0.004889019999836819, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022952960001703104, "count": 10, "is_parallel": true, "self": 0.0022952960001703104 } } }, "UnityEnvironment.step": { "total": 0.036951810000005025, "count": 1, "is_parallel": true, "self": 0.0005844190000061644, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042028599989407667, "count": 1, "is_parallel": true, "self": 0.00042028599989407667 }, "communicator.exchange": { "total": 0.034160087000032036, "count": 1, "is_parallel": true, "self": 0.034160087000032036 }, "steps_from_proto": { "total": 0.0017870180000727487, "count": 1, "is_parallel": true, "self": 0.00037043200006792176, "children": { "_process_rank_one_or_two_observation": { "total": 0.001416586000004827, "count": 10, "is_parallel": true, "self": 0.001416586000004827 } } } } } } }, "UnityEnvironment.step": { "total": 199.67357788799848, "count": 18191, "is_parallel": true, "self": 9.694810009022149, "children": { "UnityEnvironment._generate_step_input": { "total": 5.428675821998127, "count": 18191, "is_parallel": true, "self": 5.428675821998127 }, "communicator.exchange": { "total": 152.7670333039962, "count": 18191, "is_parallel": true, "self": 152.7670333039962 }, "steps_from_proto": { "total": 31.783058752982015, "count": 18191, "is_parallel": true, "self": 5.723447407998947, "children": { "_process_rank_one_or_two_observation": { "total": 26.059611344983068, "count": 181910, "is_parallel": true, "self": 26.059611344983068 } } } } } } } } } } }, "trainer_advance": { "total": 122.60759671800179, "count": 18192, "self": 0.4462921970025491, "children": { "process_trajectory": { "total": 27.898740676999296, "count": 18192, "self": 27.49108206499932, "children": { "RLTrainer._checkpoint": { "total": 0.40765861199997744, "count": 4, "self": 0.40765861199997744 } } }, "_update_policy": { "total": 94.26256384399994, "count": 90, "self": 37.92400818599731, "children": { "TorchPPOOptimizer.update": { "total": 56.33855565800263, "count": 4587, "self": 56.33855565800263 } } } } } } }, "trainer_threads": { "total": 9.009997938846936e-07, "count": 1, "self": 9.009997938846936e-07 }, "TrainerController._save_models": { "total": 0.08291965900002651, "count": 1, "self": 0.0008249750001141365, "children": { "RLTrainer._checkpoint": { "total": 0.08209468399991238, "count": 1, "self": 0.08209468399991238 } } } } } } }