{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9887726306915283, "min": 0.9887726306915283, "max": 2.8679988384246826, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9397.294921875, "min": 9397.294921875, "max": 29276.53125, "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": 12.556771278381348, "min": 0.3245188593864441, "max": 12.556771278381348, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2448.5703125, "min": 62.95665740966797, "max": 2499.161376953125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07152489814810299, "min": 0.0617977320579538, "max": 0.07611527201473055, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28609959259241197, "min": 0.2506136813545691, "max": 0.3597801441198909, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1941396557890317, "min": 0.14471976605344417, "max": 0.28903079547134103, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7765586231561268, "min": 0.5788790642137767, "max": 1.445153977356705, "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": 25.636363636363637, "min": 3.772727272727273, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 166.0, "max": 1345.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.772727272727273, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 166.0, "max": 1345.0, "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": "1772295255", "python_version": "3.10.12 (main, Jan 26 2026, 14:55:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/lib/python3.10/dist-packages/mlagents/trainers/learn.py /content/ml-agents/config/ppo/SnowballTarget_Fixed.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=Snowball_Final --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1772297364" }, "total": 2108.367676199001, "count": 1, "self": 0.638957252002001, "children": { "run_training.setup": { "total": 0.027084097999249934, "count": 1, "self": 0.027084097999249934 }, "TrainerController.start_learning": { "total": 2107.7016348489997, "count": 1, "self": 0.6091161008280324, "children": { "TrainerController._reset_env": { "total": 1.2278466150000895, "count": 1, "self": 1.2278466150000895 }, "TrainerController.advance": { "total": 2105.669962993172, "count": 18192, "self": 0.6126272402452742, "children": { "env_step": { "total": 1966.5839412750101, "count": 18192, "self": 1923.0018352609422, "children": { "SubprocessEnvManager._take_step": { "total": 43.20948449993921, "count": 18192, "self": 2.6336236400093185, "children": { "TorchPolicy.evaluate": { "total": 40.57586085992989, "count": 18192, "self": 40.57586085992989 } } }, "workers": { "total": 0.3726215141286957, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 2105.121331431974, "count": 18192, "is_parallel": true, "self": 228.88382696906228, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005141245001141215, "count": 1, "is_parallel": true, "self": 0.0009071249987755436, "children": { "_process_rank_one_or_two_observation": { "total": 0.004234120002365671, "count": 10, "is_parallel": true, "self": 0.004234120002365671 } } }, "UnityEnvironment.step": { "total": 0.22231195399945136, "count": 1, "is_parallel": true, "self": 0.0011741799989977153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0012943729998369236, "count": 1, "is_parallel": true, "self": 0.0012943729998369236 }, "communicator.exchange": { "total": 0.21331416600150988, "count": 1, "is_parallel": true, "self": 0.21331416600150988 }, "steps_from_proto": { "total": 0.006529234999106848, "count": 1, "is_parallel": true, "self": 0.0005537120014196262, "children": { "_process_rank_one_or_two_observation": { "total": 0.0059755229976872215, "count": 10, "is_parallel": true, "self": 0.0059755229976872215 } } } } } } }, "UnityEnvironment.step": { "total": 1876.2375044629116, "count": 18191, "is_parallel": true, "self": 8.622019769736653, "children": { "UnityEnvironment._generate_step_input": { "total": 25.596684056054073, "count": 18191, "is_parallel": true, "self": 25.596684056054073 }, "communicator.exchange": { "total": 1767.8237368380487, "count": 18191, "is_parallel": true, "self": 1767.8237368380487 }, "steps_from_proto": { "total": 74.19506379907216, "count": 18191, "is_parallel": true, "self": 10.375744744558688, "children": { "_process_rank_one_or_two_observation": { "total": 63.81931905451347, "count": 181910, "is_parallel": true, "self": 63.81931905451347 } } } } } } } } } } }, "trainer_advance": { "total": 138.47339447791637, "count": 18192, "self": 0.7966124339436647, "children": { "process_trajectory": { "total": 26.801289272980284, "count": 18192, "self": 26.801289272980284 }, "_update_policy": { "total": 110.87549277099242, "count": 90, "self": 63.77841348193033, "children": { "TorchPPOOptimizer.update": { "total": 47.097079289062094, "count": 4587, "self": 47.097079289062094 } } } } } } }, "trainer_threads": { "total": 9.319992386735976e-07, "count": 1, "self": 9.319992386735976e-07 }, "TrainerController._save_models": { "total": 0.19470820800052024, "count": 1, "self": 0.0009156790001725312, "children": { "RLTrainer._checkpoint": { "total": 0.1937925290003477, "count": 1, "self": 0.1937925290003477 } } } } } } }