2 papers
cs.LG2026
Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
Taewoon Kim, Vincent François-Lavet, Michael Cochez
Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term tr…
cs.RO2024
Multi-Modal Grounded Planning and Efficient Replanning For Learning Embodied Agents with A Few Examples
Taewoong Kim, Byeonghwi Kim, Jonghyun Choi
Learning a perception and reasoning module for robotic assistants to plan steps to perform complex tasks based on natural language instructions often requires large free-form langu…