Naga Ayachitula, Melissa Buco, et al.
SCC 2007
Deep reinforcement learning agents often face challenges to effectively coordinate perception and decision-making components, particularly in environments with high-dimensional sensory inputs where feature relevance varies. This work introduces SPRIG (Stackelberg Perception-Reinforcement learning with Internal Game dynamics), a framework that models the internal perception-policy interaction within a single agent as a cooperative Stackelberg game. In SPRIG, the perception module acts as a leader, strategically processing raw sensory states, while the policy module follows, making decisions based on extracted features. SPRIG provides theoretical guarantees through a modified Bellman operator while preserving the benefits of modern policy optimization. Experimental results on the Atari BeamRider environment demonstrate SPRIG's effectiveness, achieving around 30% higher returns than standard PPO through its game-theoretical balance of feature extraction and decision-making.
Naga Ayachitula, Melissa Buco, et al.
SCC 2007
Daniel J. Costello Jr., Pierre R. Chevillat, et al.
ISIT 1997
Martin Charles Golumbic, Renu C. Laskar
Discrete Applied Mathematics
Robert F. Gordon, Edward A. MacNair, et al.
WSC 1985