LGSYOCMay 27, 2022

Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space

arXiv:2205.14098v12 citationsh-index: 28
Originality Incremental advance
AI Analysis

This addresses reward optimization for POMDPs, which is an incremental improvement over existing methods.

The paper tackles reward optimization in partially observable Markov decision processes (POMDPs) with memoryless stochastic policies by formulating it as a linear objective with polynomial constraints, presenting the ROSA approach. The result shows that ROSA is computationally efficient and yields stability improvements in maze navigation tasks.

Reward optimization in fully observable Markov decision processes is equivalent to a linear program over the polytope of state-action frequencies. Taking a similar perspective in the case of partially observable Markov decision processes with memoryless stochastic policies, the problem was recently formulated as the optimization of a linear objective subject to polynomial constraints. Based on this we present an approach for Reward Optimization in State-Action space (ROSA). We test this approach experimentally in maze navigation tasks. We find that ROSA is computationally efficient and can yield stability improvements over other existing methods.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes