Continuous Control
Continuous control in the context of playing games, especially within artificial intelligence (AI) and machine learning (ML), refers to the ability to make a series of smooth, ongoing adjustments or actions to control a game or a simulation. This is in contrast to discrete control, where the actions are limited to a set of specific, distinct choices. Continuous control is crucial in environments where precision, timing, and the magnitude of actions matter, such as driving a car in a racing game, controlling a character in a simulation, or managing the flight of an aircraft in a flight simulator.
Papers
Showing 1–10 of 1161 papers
All datasetsPyBullet AntPyBullet HalfCheetahPyBullet HopperPyBullet Walker2DDeepMind Cheetah Run (Images)cartpole.balance_sparsecartpole.swingupcheetah.runDeepMind Cup Catch (Images)DeepMind Walker Walk (Images)finger.turn_hardwalker.stand
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SAC | Return | 2,883 | — | Unverified |
| 2 | SAC gSDE | Return | 2,850 | — | Unverified |
| 3 | PPO + gSDE | Return | 2,760 | — | Unverified |
| 4 | TD3 | Return | 2,687 | — | Unverified |
| 5 | TD3 gSDE | Return | 2,578 | — | Unverified |
| 6 | PPO | Return | 2,254 | — | Unverified |
| 7 | A2C + gSDE | Return | 2,028 | — | Unverified |
| 8 | A2C | Return | 1,652 | — | Unverified |