Correlation Priors For Reinforcement Learning

Abstract

Many decision-making problems naturally exhibit pronounced structures inherited from the characteristics of the underlying environment. In a Markov decision process model, for example, two distinct states can have inherently related semantics or encode resembling physical state configurations. This often implies locally correlated transition dynamics among the states. In order to complete a certain task in such environments, the operating agent usually needs to execute a series of temporally and spatially correlated actions. Though there exists a variety of approaches to capture these correlations in continuous state-action domains, a principled solution for discrete environments is missing. In this work, we present a Bayesian learning framework based on P\'olya-Gamma augmentation that enables an analogous reasoning in such cases. We demonstrate the framework on a number of common decision-making related problems, such as imitation learning, subgoal extraction, system identification an

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyalt2019correlation

Related papers

• Goal-oriented Inference Of Environment From Redundant Observations (2023)3.58
• Symbol Guided Hindsight Priors For Reward Learning From Human Preferences (2022)0.00
• Learning Symbolic Representations For Reinforcement Learning Of Non-markovian Behavior (2023)0.00
• Optimal Decision-making In Mixed-agent Partially Observable Stochastic Environments Via Reinforcement Learning (2019)0.00
• Markov Decision Processes Under External Temporal Processes (2023)0.00
• Implications Of Human Irrationality For Reinforcement Learning (2020)0.00
• Remembering The Markov Property In Cooperative MARL (2025)0.00
• A Theoretical Connection Between Statistical Physics And Reinforcement Learning (2019)0.00