{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9423902034759521, "min": 0.9423902034759521, "max": 2.859898090362549, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8956.4765625, "min": 8956.4765625, "max": 29193.83984375, "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": 12.816398620605469, "min": 0.2950589954853058, "max": 12.816398620605469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2499.19775390625, "min": 57.24144744873047, "max": 2573.84912109375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.061741000360366435, "min": 0.061741000360366435, "max": 0.0772476778538012, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24696400144146574, "min": 0.24696400144146574, "max": 0.386238389269006, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20111988828170535, "min": 0.09970296314214447, "max": 0.30335797427916056, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8044795531268214, "min": 0.3988118525685779, "max": 1.5167898713958028, "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": 25.204545454545453, "min": 2.9318181818181817, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 129.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 2.9318181818181817, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 129.0, "max": 1406.0, "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": "1755832772", "python_version": "3.10.18 (main, Aug 8 2025, 17:07:22) [Clang 20.1.4 ]", "command_line_arguments": "/home/huinker/Coding/python/.venv/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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1755832975" }, "total": 202.694405083, "count": 1, "self": 0.26835372699997606, "children": { "run_training.setup": { "total": 0.015214607999951113, "count": 1, "self": 0.015214607999951113 }, "TrainerController.start_learning": { "total": 202.41083674800007, "count": 1, "self": 0.26841272400406524, "children": { "TrainerController._reset_env": { "total": 1.6697769190000145, "count": 1, "self": 1.6697769190000145 }, "TrainerController.advance": { "total": 200.4313081239959, "count": 18192, "self": 0.28215874797297147, "children": { "env_step": { "total": 143.76388440901064, "count": 18192, "self": 112.34426943699668, "children": { "SubprocessEnvManager._take_step": { "total": 31.23544131200447, "count": 18192, "self": 0.6575951830111535, "children": { "TorchPolicy.evaluate": { "total": 30.577846128993315, "count": 18192, "self": 30.577846128993315 } } }, "workers": { "total": 0.18417366000949187, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 201.96543777899296, "count": 18192, "is_parallel": true, "self": 104.47833280298391, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011029550000785093, "count": 1, "is_parallel": true, "self": 0.0003146220001326583, "children": { "_process_rank_one_or_two_observation": { "total": 0.000788332999945851, "count": 10, "is_parallel": true, "self": 0.000788332999945851 } } }, "UnityEnvironment.step": { "total": 0.021499911000091743, "count": 1, "is_parallel": true, "self": 0.00024338599996553967, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028019100000165054, "count": 1, "is_parallel": true, "self": 0.00028019100000165054 }, "communicator.exchange": { "total": 0.020375585000010688, "count": 1, "is_parallel": true, "self": 0.020375585000010688 }, "steps_from_proto": { "total": 0.0006007490001138649, "count": 1, "is_parallel": true, "self": 0.00014840600010757043, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045234300000629446, "count": 10, "is_parallel": true, "self": 0.00045234300000629446 } } } } } } }, "UnityEnvironment.step": { "total": 97.48710497600905, "count": 18191, "is_parallel": true, "self": 3.782894856017265, "children": { "UnityEnvironment._generate_step_input": { "total": 2.501437766995423, "count": 18191, "is_parallel": true, "self": 2.501437766995423 }, "communicator.exchange": { "total": 79.73773491400175, "count": 18191, "is_parallel": true, "self": 79.73773491400175 }, "steps_from_proto": { "total": 11.465037438994614, "count": 18191, "is_parallel": true, "self": 2.4337478130612453, "children": { "_process_rank_one_or_two_observation": { "total": 9.031289625933368, "count": 181910, "is_parallel": true, "self": 9.031289625933368 } } } } } } } } } } }, "trainer_advance": { "total": 56.38526496701229, "count": 18192, "self": 0.42034302100955756, "children": { "process_trajectory": { "total": 12.868588097003112, "count": 18192, "self": 12.626173756003254, "children": { "RLTrainer._checkpoint": { "total": 0.2424143409998578, "count": 4, "self": 0.2424143409998578 } } }, "_update_policy": { "total": 43.09633384899962, "count": 90, "self": 18.242637863009804, "children": { "TorchPPOOptimizer.update": { "total": 24.853695985989816, "count": 4587, "self": 24.853695985989816 } } } } } } }, "trainer_threads": { "total": 1.1869999525515595e-06, "count": 1, "self": 1.1869999525515595e-06 }, "TrainerController._save_models": { "total": 0.04133779400012827, "count": 1, "self": 0.0006601140000839223, "children": { "RLTrainer._checkpoint": { "total": 0.04067768000004435, "count": 1, "self": 0.04067768000004435 } } } } } } }