Scaling Internal-state Policy-gradient Methods For Pomdps

Abstract

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful when memory is required. In this paper we develop several improved algorithms for learning policies with memory in an infinite-horizon setting -- directly when a known model of the environment is available, and via simulation otherwise. We compare these algorithms on some large POMDPs, including noisy robot navigation and multi-agent problems.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyaberdeen2025scaling

Related papers

• Memoryless Policy Iteration For Episodic Pomdps (2025)0.00
• A Policy Gradient Method For Confounded Pomdps (2023)0.00
• Recurrent Natural Policy Gradient For Pomdps (2024)0.00
• A Study Of Policy Gradient On A Class Of Exactly Solvable Models (2020)0.00
• Policy Gradient In Partially Observable Environments: Approximation And Convergence (2018)0.00
• Sequential Monte Carlo For Policy Optimization In Continuous Pomdps (2025)0.00
• Proximal Policy Optimization Algorithms (2017)0.00
• Robust Asymmetric Learning In Pomdps (2020)0.00