{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7967394590377808, "min": 0.7967394590377808, "max": 2.856968641281128, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7572.2119140625, "min": 7572.2119140625, "max": 29163.935546875, "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": 12.986719131469727, "min": 0.24048037827014923, "max": 12.986719131469727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2532.41015625, "min": 46.653194427490234, "max": 2627.28125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06984490175714467, "min": 0.06323237041343578, "max": 0.07433682511456187, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27937960702857867, "min": 0.2529294816537431, "max": 0.36437480283590656, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20490658049489938, "min": 0.10011287998093071, "max": 0.2718416042625904, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8196263219795975, "min": 0.40045151992372285, "max": 1.3307207644570107, "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": 25.795454545454547, "min": 3.340909090909091, "max": 25.927272727272726, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 147.0, "max": 1426.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.340909090909091, "max": 25.927272727272726, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 147.0, "max": 1426.0, "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": "1749157648", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749158206" }, "total": 557.8184926380001, "count": 1, "self": 0.6538714429999573, "children": { "run_training.setup": { "total": 0.02731553299997813, "count": 1, "self": 0.02731553299997813 }, "TrainerController.start_learning": { "total": 557.1373056620001, "count": 1, "self": 0.5226525020012787, "children": { "TrainerController._reset_env": { "total": 3.895893172000001, "count": 1, "self": 3.895893172000001 }, "TrainerController.advance": { "total": 552.6013464939989, "count": 18192, "self": 0.5678610509916098, "children": { "env_step": { "total": 397.888348916008, "count": 18192, "self": 304.08426041501195, "children": { "SubprocessEnvManager._take_step": { "total": 93.47043198199424, "count": 18192, "self": 1.7831242449771025, "children": { "TorchPolicy.evaluate": { "total": 91.68730773701714, "count": 18192, "self": 91.68730773701714 } } }, "workers": { "total": 0.3336565190018064, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 555.218418264013, "count": 18192, "is_parallel": true, "self": 291.15670017302784, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0064958839999462725, "count": 1, "is_parallel": true, "self": 0.00478006100024686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017158229996994123, "count": 10, "is_parallel": true, "self": 0.0017158229996994123 } } }, "UnityEnvironment.step": { "total": 0.07032261099993775, "count": 1, "is_parallel": true, "self": 0.000764896999839948, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040469099997153535, "count": 1, "is_parallel": true, "self": 0.00040469099997153535 }, "communicator.exchange": { "total": 0.0669497080000383, "count": 1, "is_parallel": true, "self": 0.0669497080000383 }, "steps_from_proto": { "total": 0.0022033150000879687, "count": 1, "is_parallel": true, "self": 0.00042914200014365633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017741729999443123, "count": 10, "is_parallel": true, "self": 0.0017741729999443123 } } } } } } }, "UnityEnvironment.step": { "total": 264.0617180909852, "count": 18191, "is_parallel": true, "self": 12.626080302975879, "children": { "UnityEnvironment._generate_step_input": { "total": 6.702000017003229, "count": 18191, "is_parallel": true, "self": 6.702000017003229 }, "communicator.exchange": { "total": 205.65008899798693, "count": 18191, "is_parallel": true, "self": 205.65008899798693 }, "steps_from_proto": { "total": 39.083548773019174, "count": 18191, "is_parallel": true, "self": 7.3965862590437155, "children": { "_process_rank_one_or_two_observation": { "total": 31.68696251397546, "count": 181910, "is_parallel": true, "self": 31.68696251397546 } } } } } } } } } } }, "trainer_advance": { "total": 154.1451365269993, "count": 18192, "self": 0.6895044049954322, "children": { "process_trajectory": { "total": 33.02882986600309, "count": 18192, "self": 32.54128960500316, "children": { "RLTrainer._checkpoint": { "total": 0.4875402609999355, "count": 4, "self": 0.4875402609999355 } } }, "_update_policy": { "total": 120.42680225600077, "count": 90, "self": 48.738676088000716, "children": { "TorchPPOOptimizer.update": { "total": 71.68812616800005, "count": 4587, "self": 71.68812616800005 } } } } } } }, "trainer_threads": { "total": 1.1859999631269602e-06, "count": 1, "self": 1.1859999631269602e-06 }, "TrainerController._save_models": { "total": 0.11741230799998448, "count": 1, "self": 0.000987420999990718, "children": { "RLTrainer._checkpoint": { "total": 0.11642488699999376, "count": 1, "self": 0.11642488699999376 } } } } } } }