Agent-state Based Policies In Pomdps: Beyond Belief-state Mdps

Abstract

The traditional approach to POMDPs is to convert them into fully observed MDPs by considering a belief state as an information state. However, a belief-state based approach requires perfect knowledge of the system dynamics and is therefore not applicable in the learning setting where the system model is unknown. Various approaches to circumvent this limitation have been proposed in the literature. We present a unified treatment of some of these approaches by viewing them as models where the agent maintains a local recursively updateable agent state and chooses actions based on the agent state. We highlight the different classes of agent-state based policies and the various approaches that have been proposed in the literature to find good policies within each class. These include the designer's approach to find optimal non-stationary agent-state based policies, policy search approaches to find a locally optimal stationary agent-state based policies, and the approximate information state

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysinha2024agent

Related papers

• How To Explore With Belief: State Entropy Maximization In Pomdps (2024)0.00
• Off-belief Learning (2021)0.00
• Model-based Learning Of Near-optimal Finite-window Policies In Pomdps (2026)0.00
• Scaling Internal-state Policy-gradient Methods For Pomdps (2025)0.00
• Robust Asymmetric Learning In Pomdps (2020)0.00
• Enforcing Almost-sure Reachability In Pomdps (2020)0.00
• Policy Evaluation In Decentralized Pomdps With Belief Sharing (2023)0.00
• Common Information Based Approximate State Representations In Multi-agent Reinforcement Learning (2021)0.00