Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search
We present a method for synthesizing reactive character behaviors for continuous games as compact, human-readable programs. Game AI practice still relies heavily on manually authored behavior trees, state machines, and scripts, while academic reinforcement learning typically produces opaque neural controllers that are...
Maxim Gumin, Hsueh-Ti Derek Liu, Victor B. Zordan et al.
· 0 citations