persona-conditioning

Tag

Cards List
#persona-conditioning

One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents

arXiv cs.AI · 2026-05-25 Cached

Introduces PCSP, a single RL policy conditioned on frozen LLM embeddings of persona descriptions, enabling scalable, real-time persona-traceable NPC control in life simulation games. Experiments show zero-shot persona identification and behavioral alignment, with faster inference than LLM baselines.

0 favorites 0 likes
← Back to home

Submit Feedback