{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9458447694778442, "min": 0.9252396821975708, "max": 2.840425729751587, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8989.30859375, "min": 8989.30859375, "max": 28995.06640625, "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": 13.001035690307617, "min": 0.31375253200531006, "max": 13.001035690307617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.201904296875, "min": 60.86799240112305, "max": 2634.70068359375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07197167271264263, "min": 0.057902310665311096, "max": 0.07366879364189136, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2878866908505705, "min": 0.23160924266124439, "max": 0.35665459202901534, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21984249309581866, "min": 0.13560704664696993, "max": 0.299727312431616, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8793699723832746, "min": 0.5424281865878797, "max": 1.49863656215808, "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": 25.363636363636363, "min": 4.0, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 176.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 4.0, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 176.0, "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": "1748318644", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748319089" }, "total": 445.13086093799996, "count": 1, "self": 0.4893285210000613, "children": { "run_training.setup": { "total": 0.03413372199997866, "count": 1, "self": 0.03413372199997866 }, "TrainerController.start_learning": { "total": 444.6073986949999, "count": 1, "self": 0.43612846200005606, "children": { "TrainerController._reset_env": { "total": 3.767373803000055, "count": 1, "self": 3.767373803000055 }, "TrainerController.advance": { "total": 440.2704957709998, "count": 18192, "self": 0.4543552290080015, "children": { "env_step": { "total": 314.0065434689983, "count": 18192, "self": 240.1415595740067, "children": { "SubprocessEnvManager._take_step": { "total": 73.61359837099064, "count": 18192, "self": 1.359710294987508, "children": { "TorchPolicy.evaluate": { "total": 72.25388807600314, "count": 18192, "self": 72.25388807600314 } } }, "workers": { "total": 0.25138552400096614, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 442.99207105299445, "count": 18192, "is_parallel": true, "self": 233.2866068449964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005770614999960344, "count": 1, "is_parallel": true, "self": 0.004320903000120779, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014497119998395647, "count": 10, "is_parallel": true, "self": 0.0014497119998395647 } } }, "UnityEnvironment.step": { "total": 0.038310198999965905, "count": 1, "is_parallel": true, "self": 0.0005970050000314586, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003847680000035325, "count": 1, "is_parallel": true, "self": 0.0003847680000035325 }, "communicator.exchange": { "total": 0.035417721999920104, "count": 1, "is_parallel": true, "self": 0.035417721999920104 }, "steps_from_proto": { "total": 0.00191070400001081, "count": 1, "is_parallel": true, "self": 0.00037556699999186094, "children": { "_process_rank_one_or_two_observation": { "total": 0.001535137000018949, "count": 10, "is_parallel": true, "self": 0.001535137000018949 } } } } } } }, "UnityEnvironment.step": { "total": 209.70546420799803, "count": 18191, "is_parallel": true, "self": 10.12119845600273, "children": { "UnityEnvironment._generate_step_input": { "total": 5.487875074998669, "count": 18191, "is_parallel": true, "self": 5.487875074998669 }, "communicator.exchange": { "total": 162.06302647000018, "count": 18191, "is_parallel": true, "self": 162.06302647000018 }, "steps_from_proto": { "total": 32.03336420699645, "count": 18191, "is_parallel": true, "self": 6.041270980006971, "children": { "_process_rank_one_or_two_observation": { "total": 25.992093226989482, "count": 181910, "is_parallel": true, "self": 25.992093226989482 } } } } } } } } } } }, "trainer_advance": { "total": 125.80959707299348, "count": 18192, "self": 0.5877490259994147, "children": { "process_trajectory": { "total": 27.75991434099376, "count": 18192, "self": 27.27558980399374, "children": { "RLTrainer._checkpoint": { "total": 0.4843245370000204, "count": 4, "self": 0.4843245370000204 } } }, "_update_policy": { "total": 97.46193370600031, "count": 90, "self": 39.763384395001935, "children": { "TorchPPOOptimizer.update": { "total": 57.698549310998374, "count": 4587, "self": 57.698549310998374 } } } } } } }, "trainer_threads": { "total": 1.3670000953425188e-06, "count": 1, "self": 1.3670000953425188e-06 }, "TrainerController._save_models": { "total": 0.13339929199992184, "count": 1, "self": 0.0010549809999247373, "children": { "RLTrainer._checkpoint": { "total": 0.1323443109999971, "count": 1, "self": 0.1323443109999971 } } } } } } }