Reinforcement Learning in POMDP's via Direct Gradient Ascent

• URL: http://arxiv.org/abs/2512.02383v1
• Date: Tue, 02 Dec 2025 03:50:06 GMT
• Title: Reinforcement Learning in POMDP's via Direct Gradient Ascent
• Authors: Jonathan Baxter, Peter L. Bartlett,
• Abstract summary: We introduce GPOMDP, a REINFORCE-like algorithm for estimating an approximation to the gradient of the average reward.<n>We show how GPOMDP can be used in a conjugate-gradient procedure to find local optima of the average reward.
• Score: 21.715823431124235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled POMDPs. We introduce GPOMDP, a REINFORCE-like algorithm for estimating an approximation to the gradient of the average reward as a function of the parameters of a stochastic policy. The algorithm's chief advantages are that it requires only a single sample path of the underlying Markov chain, it uses only one free parameter $β\in [0,1)$, which has a natural interpretation in terms of bias-variance trade-off, and it requires no knowledge of the underlying state. We prove convergence of GPOMDP and show how the gradient estimates produced by GPOMDP can be used in a conjugate-gradient procedure to find local optima of the average reward.

Related papers

• ISOPO: Proximal policy gradients without pi-old [0.0]
  ISOPO is an efficient method to approximate the natural policy gradient in a single step.<n>It can be implemented with negligible computational overhead compared to vanilla REINFORCE.
  arXiv  Detail & Related papers  (2025-12-29T10:30:29Z)
• Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models [69.1820058966619]
  We tackle average-reward infinite-horizon POMDPs with an unknown transition model.<n>We present a novel and simple estimator that overcomes this barrier.
  arXiv  Detail & Related papers  (2025-01-30T22:29:41Z)
• Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting [56.92178753201331]
  We propose the Observation-Aware Spectral (OAS) estimation technique, which enables the POMDP parameters to be learned from samples collected using a belief-based policy. We show the consistency of the OAS procedure, and we prove a regret guarantee of order $mathcalO(sqrtT log(T)$ for the proposed OAS-UCRL algorithm.
  arXiv  Detail & Related papers  (2024-10-02T08:46:34Z)
• Strongly-polynomial time and validation analysis of policy gradient methods [3.722665817361884]
  This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL)<n>By incorporating this advantage gap function into the design of step size rules, we deriving a new linear rate of convergence that is independent of the stationary state distribution of the optimal policy.<n>This is the first time that such strong convergence properties have been established for policy gradient methods.
  arXiv  Detail & Related papers  (2024-09-28T18:56:48Z)
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [15.038210624870656]
  Reward inference is a critical intermediate step in the Reinforcement Learning from Human Feedback pipeline.<n>This paper develops two RLHF algorithms without reward inference for general RL problems beyond bandits and deterministic MDP bandit, and general preference models beyond the Bradley-Terry model.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes [50.68789924454235]
  We present the first finite time global convergence analysis of policy gradient in the context of average reward Markov decision processes (MDPs) Our analysis shows that the policy gradient iterates converge to the optimal policy at a sublinear rate of $Oleft(frac1Tright),$ which translates to $Oleft(log(T)right)$ regret, where $T$ represents the number of iterations.
  arXiv  Detail & Related papers  (2024-03-11T15:25:03Z)
• Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability [2.180257135067774]
  We introduce a policy-gradient method for model-based reinforcement learning (RL)<n>We exploit a type of stationary distributions commonly obtained from Markov decision processes (MDPs) in networks.<n>We show that SAGE-based policy-gradient locally converges, and we obtain its regret.
  arXiv  Detail & Related papers  (2023-12-05T14:44:58Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• Logistic Q-Learning [87.00813469969167]
  We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The main feature of our algorithm is a convex loss function for policy evaluation that serves as a theoretically sound alternative to the widely used squared Bellman error.
  arXiv  Detail & Related papers  (2020-10-21T17:14:31Z)
• PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning [35.044047991893365]
  This work introduces the the Policy Cover-Policy Gradient (PC-PG) algorithm, which balances the exploration vs. exploitation tradeoff using an ensemble of policies (the policy cover) We show that PC-PG has strong guarantees under model misspecification that go beyond the standard worst case $ell_infty$ assumptions. We also complement the theory with empirical evaluation across a variety of domains in both reward-free and reward-driven settings.
  arXiv  Detail & Related papers  (2020-07-16T16:57:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.