{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8360552191734314, "min": 0.816853940486908, "max": 2.8527119159698486, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7945.86865234375, "min": 7945.86865234375, "max": 29120.484375, "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": 13.13743782043457, "min": 0.4039364159107208, "max": 13.13743782043457, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2561.80029296875, "min": 78.36366271972656, "max": 2667.9453125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07033806120435818, "min": 0.06382793796293816, "max": 0.07699043558044222, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2813522448174327, "min": 0.25531175185175264, "max": 0.38219940024810417, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18998282267620753, "min": 0.13133907924273835, "max": 0.3126400228808908, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7599312907048301, "min": 0.5253563169709534, "max": 1.563200114404454, "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": 25.90909090909091, "min": 3.6818181818181817, "max": 25.98181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 162.0, "max": 1429.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.6818181818181817, "max": 25.98181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 162.0, "max": 1429.0, "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": "1774124122", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1774124571" }, "total": 448.7585748780002, "count": 1, "self": 0.6427439330000198, "children": { "run_training.setup": { "total": 0.022844670000267797, "count": 1, "self": 0.022844670000267797 }, "TrainerController.start_learning": { "total": 448.09298627499993, "count": 1, "self": 0.348408810107685, "children": { "TrainerController._reset_env": { "total": 2.933731789000376, "count": 1, "self": 2.933731789000376 }, "TrainerController.advance": { "total": 444.7020781628926, "count": 18192, "self": 0.3748609448593925, "children": { "env_step": { "total": 325.52419450601246, "count": 18192, "self": 255.07841976312466, "children": { "SubprocessEnvManager._take_step": { "total": 70.23122316894114, "count": 18192, "self": 1.268456923931808, "children": { "TorchPolicy.evaluate": { "total": 68.96276624500933, "count": 18192, "self": 68.96276624500933 } } }, "workers": { "total": 0.21455157394666458, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 445.9928178030341, "count": 18192, "is_parallel": true, "self": 221.35926833404392, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007780244000059611, "count": 1, "is_parallel": true, "self": 0.006460854002398264, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013193899976613466, "count": 10, "is_parallel": true, "self": 0.0013193899976613466 } } }, "UnityEnvironment.step": { "total": 0.07396770100058347, "count": 1, "is_parallel": true, "self": 0.0005400999998528278, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004982200007361826, "count": 1, "is_parallel": true, "self": 0.0004982200007361826 }, "communicator.exchange": { "total": 0.0690322020000167, "count": 1, "is_parallel": true, "self": 0.0690322020000167 }, "steps_from_proto": { "total": 0.0038971789999777684, "count": 1, "is_parallel": true, "self": 0.0003395079993424588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0035576710006353096, "count": 10, "is_parallel": true, "self": 0.0035576710006353096 } } } } } } }, "UnityEnvironment.step": { "total": 224.63354946899017, "count": 18191, "is_parallel": true, "self": 10.49950004789207, "children": { "UnityEnvironment._generate_step_input": { "total": 5.736464434996378, "count": 18191, "is_parallel": true, "self": 5.736464434996378 }, "communicator.exchange": { "total": 170.3553951800841, "count": 18191, "is_parallel": true, "self": 170.3553951800841 }, "steps_from_proto": { "total": 38.04218980601763, "count": 18191, "is_parallel": true, "self": 6.754985638236576, "children": { "_process_rank_one_or_two_observation": { "total": 31.287204167781056, "count": 181910, "is_parallel": true, "self": 31.287204167781056 } } } } } } } } } } }, "trainer_advance": { "total": 118.80302271202072, "count": 18192, "self": 0.4358344800011764, "children": { "process_trajectory": { "total": 26.922175023019008, "count": 18192, "self": 26.449681822019556, "children": { "RLTrainer._checkpoint": { "total": 0.4724932009994518, "count": 4, "self": 0.4724932009994518 } } }, "_update_policy": { "total": 91.44501320900054, "count": 90, "self": 37.389853921015856, "children": { "TorchPPOOptimizer.update": { "total": 54.05515928798468, "count": 4587, "self": 54.05515928798468 } } } } } } }, "trainer_threads": { "total": 1.2809996405849233e-06, "count": 1, "self": 1.2809996405849233e-06 }, "TrainerController._save_models": { "total": 0.10876623199965252, "count": 1, "self": 0.0008435370000370312, "children": { "RLTrainer._checkpoint": { "total": 0.10792269499961549, "count": 1, "self": 0.10792269499961549 } } } } } } }