A Survey of Knowledge-based Sequential Decision Making under Uncertainty

Abstract

Reasoning with declarative knowledge (RDK) and sequential decision-making (SDM) are two key research areas in artificial intelligence. RDK methods reason with declarative domain knowledge, including commonsense knowledge, that is either provided a priori or acquired over time, while SDM methods (probabilistic planning and reinforcement learning) seek to compute action policies that maximize the expected cumulative utility over a time horizon; both classes of methods reason in the presence of uncertainty. Despite the rich literature in these two areas, researchers have not fully explored their complementary strengths. In this paper, we survey algorithms that leverage RDK methods while making sequential decisions under uncertainty. We discuss significant developments, open problems, and directions for future work.

AI Magazine, Volume 43, Issue 2, Pages 249-266, 2022

References in corpus (9)

• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
• Towards Deep Symbolic Reinforcement Learning
• Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
• Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
• Learning Compact Models for Planning with Exogenous Processes
• Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialog
• Bridging Commonsense Reasoning and Probabilistic Planning via a Probabilistic Action Language
• iCORPP: Interleaved Commonsense Reasoning and Probabilistic Planning on Robots
• Model Checking with Probabilistic Tabled Logic Programming

Cited by in corpus (2)

• Structure in Deep Reinforcement Learning: A Survey and Open Problems
• The Logical Options Framework