{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0360431671142578, "min": 1.0360431671142578, "max": 2.8493521213531494, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9903.537109375, "min": 9903.537109375, "max": 29211.55859375, "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": 12.50070571899414, "min": 0.41356712579727173, "max": 12.50070571899414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2437.6376953125, "min": 80.23202514648438, "max": 2520.25537109375, "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": 0.07111268791406616, "min": 0.0631952129424819, "max": 0.07444560893297117, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28445075165626466, "min": 0.2527808517699276, "max": 0.37115418937116607, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19298376077238252, "min": 0.13861848706808672, "max": 0.27624806696001225, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7719350430895301, "min": 0.5544739482723469, "max": 1.304868332311219, "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": 25.0, "min": 3.7954545454545454, "max": 25.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 167.0, "max": 1343.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.7954545454545454, "max": 25.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 167.0, "max": 1343.0, "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": "1723051368", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723051798" }, "total": 429.671464589, "count": 1, "self": 0.423988157999986, "children": { "run_training.setup": { "total": 0.0536184690000141, "count": 1, "self": 0.0536184690000141 }, "TrainerController.start_learning": { "total": 429.193857962, "count": 1, "self": 0.49793900999236484, "children": { "TrainerController._reset_env": { "total": 2.7600310280000144, "count": 1, "self": 2.7600310280000144 }, "TrainerController.advance": { "total": 425.8438240770075, "count": 18202, "self": 0.2393189400048641, "children": { "env_step": { "total": 425.60450513700266, "count": 18202, "self": 274.6899566600065, "children": { "SubprocessEnvManager._take_step": { "total": 150.64891226799915, "count": 18202, "self": 1.385819379006989, "children": { "TorchPolicy.evaluate": { "total": 149.26309288899216, "count": 18202, "self": 149.26309288899216 } } }, "workers": { "total": 0.265636208997023, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 428.1764398799862, "count": 18202, "is_parallel": true, "self": 217.3980996599878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005922385000019403, "count": 1, "is_parallel": true, "self": 0.0044266280000897495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014957569999296538, "count": 10, "is_parallel": true, "self": 0.0014957569999296538 } } }, "UnityEnvironment.step": { "total": 0.03725406300003442, "count": 1, "is_parallel": true, "self": 0.000617624000028627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000375448999989203, "count": 1, "is_parallel": true, "self": 0.000375448999989203 }, "communicator.exchange": { "total": 0.034425012999975024, "count": 1, "is_parallel": true, "self": 0.034425012999975024 }, "steps_from_proto": { "total": 0.0018359770000415665, "count": 1, "is_parallel": true, "self": 0.0003323769999497017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015036000000918648, "count": 10, "is_parallel": true, "self": 0.0015036000000918648 } } } } } } }, "UnityEnvironment.step": { "total": 210.77834021999843, "count": 18201, "is_parallel": true, "self": 9.589128664993723, "children": { "UnityEnvironment._generate_step_input": { "total": 5.017942707004352, "count": 18201, "is_parallel": true, "self": 5.017942707004352 }, "communicator.exchange": { "total": 164.74009572500682, "count": 18201, "is_parallel": true, "self": 164.74009572500682 }, "steps_from_proto": { "total": 31.431173122993528, "count": 18201, "is_parallel": true, "self": 5.767088807999244, "children": { "_process_rank_one_or_two_observation": { "total": 25.664084314994284, "count": 182010, "is_parallel": true, "self": 25.664084314994284 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011125800006084319, "count": 1, "self": 0.00011125800006084319, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 420.7165697349815, "count": 645961, "is_parallel": true, "self": 12.954802657869493, "children": { "process_trajectory": { "total": 233.70749598211148, "count": 645961, "is_parallel": true, "self": 233.05891984311165, "children": { "RLTrainer._checkpoint": { "total": 0.6485761389998288, "count": 4, "is_parallel": true, "self": 0.6485761389998288 } } }, "_update_policy": { "total": 174.0542710950005, "count": 90, "is_parallel": true, "self": 53.976094208996244, "children": { "TorchPPOOptimizer.update": { "total": 120.07817688600426, "count": 4587, "is_parallel": true, "self": 120.07817688600426 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0919525890000159, "count": 1, "self": 0.0010066140000617452, "children": { "RLTrainer._checkpoint": { "total": 0.09094597499995416, "count": 1, "self": 0.09094597499995416 } } } } } } }