{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9303058981895447, "min": 0.9303058981895447, "max": 2.861947774887085, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8882.560546875, "min": 8882.560546875, "max": 29309.20703125, "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": 12.777238845825195, "min": 0.3694853186607361, "max": 12.777238845825195, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2491.5615234375, "min": 71.6801528930664, "max": 2597.496337890625, "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": 0.07269376351837754, "min": 0.05834260093812084, "max": 0.07805073744869635, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2907750540735102, "min": 0.2520980193735073, "max": 0.3849109407513192, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2055492367522389, "min": 0.11147841807299605, "max": 0.2847730640833284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8221969470089556, "min": 0.4459136722919842, "max": 1.407638548635969, "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": 24.954545454545453, "min": 3.340909090909091, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 147.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.340909090909091, "max": 25.436363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 147.0, "max": 1399.0, "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": "1702428479", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702428972" }, "total": 492.555256547, "count": 1, "self": 0.44405893200001856, "children": { "run_training.setup": { "total": 0.13793646099998114, "count": 1, "self": 0.13793646099998114 }, "TrainerController.start_learning": { "total": 491.973261154, "count": 1, "self": 0.6311254640034463, "children": { "TrainerController._reset_env": { "total": 3.823728096000025, "count": 1, "self": 3.823728096000025 }, "TrainerController.advance": { "total": 487.4310355149965, "count": 18200, "self": 0.30526833100879003, "children": { "env_step": { "total": 487.1257671839877, "count": 18200, "self": 331.1848526319766, "children": { "SubprocessEnvManager._take_step": { "total": 155.62848163500496, "count": 18200, "self": 1.5540785750002328, "children": { "TorchPolicy.evaluate": { "total": 154.07440306000473, "count": 18200, "self": 154.07440306000473 } } }, "workers": { "total": 0.3124329170061628, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 490.63758858098817, "count": 18200, "is_parallel": true, "self": 239.0208947109935, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005917941999996401, "count": 1, "is_parallel": true, "self": 0.004385425000009491, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015325169999869104, "count": 10, "is_parallel": true, "self": 0.0015325169999869104 } } }, "UnityEnvironment.step": { "total": 0.09641219999997475, "count": 1, "is_parallel": true, "self": 0.0007554139999683684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039016499999888765, "count": 1, "is_parallel": true, "self": 0.00039016499999888765 }, "communicator.exchange": { "total": 0.09320884100003468, "count": 1, "is_parallel": true, "self": 0.09320884100003468 }, "steps_from_proto": { "total": 0.0020577799999728086, "count": 1, "is_parallel": true, "self": 0.0004047749999926964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016530049999801122, "count": 10, "is_parallel": true, "self": 0.0016530049999801122 } } } } } } }, "UnityEnvironment.step": { "total": 251.61669386999466, "count": 18199, "is_parallel": true, "self": 10.910188291990949, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5413000009946245, "count": 18199, "is_parallel": true, "self": 5.5413000009946245 }, "communicator.exchange": { "total": 200.03740661800128, "count": 18199, "is_parallel": true, "self": 200.03740661800128 }, "steps_from_proto": { "total": 35.127798959007805, "count": 18199, "is_parallel": true, "self": 6.80495695200193, "children": { "_process_rank_one_or_two_observation": { "total": 28.322842007005875, "count": 181990, "is_parallel": true, "self": 28.322842007005875 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.5260000004200265e-05, "count": 1, "self": 3.5260000004200265e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.32968073803534, "count": 516163, "is_parallel": true, "self": 11.024666929041587, "children": { "process_trajectory": { "total": 273.4568063019942, "count": 516163, "is_parallel": true, "self": 272.7194654769944, "children": { "RLTrainer._checkpoint": { "total": 0.7373408249998192, "count": 4, "is_parallel": true, "self": 0.7373408249998192 } } }, "_update_policy": { "total": 198.84820750699953, "count": 90, "is_parallel": true, "self": 60.569814651997945, "children": { "TorchPPOOptimizer.update": { "total": 138.27839285500158, "count": 4587, "is_parallel": true, "self": 138.27839285500158 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08733681900002921, "count": 1, "self": 0.0009003620000385126, "children": { "RLTrainer._checkpoint": { "total": 0.0864364569999907, "count": 1, "self": 0.0864364569999907 } } } } } } }