{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9812768697738647, "min": 0.975520670413971, "max": 2.8683207035064697, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9358.4375, "min": 9358.4375, "max": 29437.57421875, "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": 12.896549224853516, "min": 0.4801107943058014, "max": 12.896549224853516, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2514.8271484375, "min": 93.14149475097656, "max": 2616.41455078125, "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.Losses.PolicyLoss.mean": { "value": 0.06279528794688054, "min": 0.06279528794688054, "max": 0.07386226462104412, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25118115178752215, "min": 0.25118115178752215, "max": 0.3693113231052206, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22950710999030693, "min": 0.1321731962482719, "max": 0.31209872943513534, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9180284399612277, "min": 0.5286927849930876, "max": 1.5604936471756767, "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.CumulativeReward.mean": { "value": 25.022727272727273, "min": 3.727272727272727, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 164.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.727272727272727, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 164.0, "max": 1408.0, "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": "1737037797", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737038371" }, "total": 574.1508459500001, "count": 1, "self": 0.5973476280000796, "children": { "run_training.setup": { "total": 0.024668802999997297, "count": 1, "self": 0.024668802999997297 }, "TrainerController.start_learning": { "total": 573.528829519, "count": 1, "self": 0.8477829259961709, "children": { "TrainerController._reset_env": { "total": 3.126226673000019, "count": 1, "self": 3.126226673000019 }, "TrainerController.advance": { "total": 569.4664474300039, "count": 18202, "self": 0.4165862070182129, "children": { "env_step": { "total": 569.0498612229857, "count": 18202, "self": 438.33819404099603, "children": { "SubprocessEnvManager._take_step": { "total": 130.29784191700168, "count": 18202, "self": 2.340918872015095, "children": { "TorchPolicy.evaluate": { "total": 127.95692304498658, "count": 18202, "self": 127.95692304498658 } } }, "workers": { "total": 0.41382526498796324, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 571.5587180309965, "count": 18202, "is_parallel": true, "self": 265.0254990159862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007106636000003164, "count": 1, "is_parallel": true, "self": 0.004351427000074182, "children": { "_process_rank_one_or_two_observation": { "total": 0.002755208999928982, "count": 10, "is_parallel": true, "self": 0.002755208999928982 } } }, "UnityEnvironment.step": { "total": 0.10390899800000852, "count": 1, "is_parallel": true, "self": 0.0007416810000790974, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044642699998576063, "count": 1, "is_parallel": true, "self": 0.00044642699998576063 }, "communicator.exchange": { "total": 0.09503079899997147, "count": 1, "is_parallel": true, "self": 0.09503079899997147 }, "steps_from_proto": { "total": 0.007690090999972199, "count": 1, "is_parallel": true, "self": 0.005712659999971947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019774310000002515, "count": 10, "is_parallel": true, "self": 0.0019774310000002515 } } } } } } }, "UnityEnvironment.step": { "total": 306.5332190150103, "count": 18201, "is_parallel": true, "self": 14.135163399022531, "children": { "UnityEnvironment._generate_step_input": { "total": 7.546580039997821, "count": 18201, "is_parallel": true, "self": 7.546580039997821 }, "communicator.exchange": { "total": 240.91427740299486, "count": 18201, "is_parallel": true, "self": 240.91427740299486 }, "steps_from_proto": { "total": 43.93719817299507, "count": 18201, "is_parallel": true, "self": 8.758904791992109, "children": { "_process_rank_one_or_two_observation": { "total": 35.17829338100296, "count": 182010, "is_parallel": true, "self": 35.17829338100296 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019187199995940318, "count": 1, "self": 0.00019187199995940318, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 562.1464733190963, "count": 789849, "is_parallel": true, "self": 18.365904553055202, "children": { "process_trajectory": { "total": 305.4843771960413, "count": 789849, "is_parallel": true, "self": 304.43697047704126, "children": { "RLTrainer._checkpoint": { "total": 1.047406719000037, "count": 4, "is_parallel": true, "self": 1.047406719000037 } } }, "_update_policy": { "total": 238.2961915699998, "count": 90, "is_parallel": true, "self": 65.36884002900115, "children": { "TorchPPOOptimizer.update": { "total": 172.92735154099864, "count": 4587, "is_parallel": true, "self": 172.92735154099864 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08818061800002397, "count": 1, "self": 0.0013238410000440126, "children": { "RLTrainer._checkpoint": { "total": 0.08685677699997996, "count": 1, "self": 0.08685677699997996 } } } } } } }