Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper addresses the challenge of estimating policy gradients in partially observable Markov decision processes (POMDPs). We propose GPOMDP, a direct policy gradient estimation algorithm that operates on a single trajectory and involves only one tunable parameter. GPOMDP extends the REINFORCE framework to average-reward optimization in POMDPs without requiring a transition model or prior domain knowledge. Its gradient estimator admits an explicit bias–variance trade-off interpretation and can be integrated with conjugate gradient methods to accelerate convergence. We provide theoretical convergence guarantees for the algorithm under standard regularity conditions. Empirical evaluations demonstrate that GPOMDP robustly approximates the true policy gradient in complex POMDP environments and reliably converges to locally optimal policies maximizing the average reward.