5 papers
Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents
Quang Dao, Purvi Kathalkar, Kenneth Eaton
Large language model (LLM) agents have demonstrated the ability to solve multi-step tasks requiring planning, tool use, and external information access, yet growing execution histo…
World Model Robustness via Surprise Recognition
Geigh Zollicoffer, Tanush Chopra, Mingkuan Yan +3
AI systems deployed in the real world must contend with distractions and out-of-distribution (OOD) noise that can destabilize their policies and lead to unsafe behavior. While robu…
The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited
Kenneth Eaton, Jonathan Balloch, Julia Kim +1
Interpretability of deep reinforcement learning systems could assist operators with understanding how they interact with their environment. Vector quantization methods -- also call…
Using Analytics on Student Created Data to Content Validate Pedagogical Tools
John Kos, Kenneth Eaton, Sareen Zhang +4
Conceptual and simulation models can function as useful pedagogical tools, however it is important to categorize different outcomes when evaluating them in order to more meaningful…
Novelty Detection in Reinforcement Learning with World Models
Geigh Zollicoffer, Kenneth Eaton, Jonathan Balloch +4
Reinforcement learning (RL) using world models has found significant recent successes. However, when a sudden change to world mechanics or properties occurs then agent performance…