6 papers
What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning
Hyeonchang Jeon, Kyungbeom Kim, Eugene Vinitsky +1
Large-scale datasets and fast simulators have enabled improvements in driving policies that appear safe and robust, yet strong performance in nominal scenarios can still mask flawe…
Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL
Sung-Hyun Kim, Geum-Hwan Hwang, In-Chang Baek +2
Recent advancements in generative modeling emphasize the importance of natural language as a highly expressive and accessible modality for controlling content generation. However,…
Automatic Curriculum Design for Zero-Shot Human-AI Coordination
Won-Sang You, Tae-Gwan Ha, Seo-Young Lee +1
Zero-shot human-AI coordination is the training of an ego-agent to coordinate with humans without human data. Most studies on zero-shot human-AI coordination have focused on enhanc…
Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation
In-Chang Baek, Seoyoung Lee, Sung-Hyun Kim +2
Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals…
IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation
In-Chang Baek, Sung-Hyun Kim, Seo-Young Lee +2
Recent research has highlighted the significance of natural language in enhancing the controllability of generative models. While various efforts have been made to leverage natural…
Discrete Prompt Compression with Reinforcement Learning
Hoyoun Jung, Kyung-Joong Kim
Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which primarily based on…