Fitted Q-iteration by Advantage Weighted Regression
Recently, fitted Q-iteration (FQI) based methods have become more popular due to their increased sample efficiency, a more stable learning process and the higher quality of the resulting policy. However, these methods remain hard to use for continuous action spaces which frequently occur in real-world tasks, e.g., in robotics and other technical applications. The greedy action selection commonly used for the policy improvement step is particularly problematic as it is expensive for continuous actions, can cause an unstable learning process, introduces an optimization bias and results in highly non-smooth policies unsuitable for real-world systems. In this paper, we show that by using a soft-greedy action selection the policy improvement step used in FQI can be simplified to an inexpensive advantage-weighted regression. With this result, we are able to derive a new, computationally efficient FQI algorithm which can even deal with high dimensional action spaces.
Code (0)
등록된 구현이 없습니다.
Tasks
regressionSimilar Papers 제목 키워드 기반
Boosted Fitted Q-Iteration
This paper is about the study of B-FQI, an Approximated Value Iteration (AVI) algorithm that exploits a boosting procedure to estimate the action-value function in reinforcement learning problems. B-FQI is an iterat…
regressionReinforcement LearningGeneralization Error Estimation for Primal--Dual Algorithms in Non-Smooth Regression
This paper studies trajectory-wise estimation of generalization error for primal--dual algorithms in non-smooth regression. Motivating examples include \(\ell_1\)-penalized least absolute deviations regression and square…
Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting
Fitted \(Q\)-evaluation (FQE) is a standard regression-based method for off-policy evaluation, but under distribution shift, value-function realizability alone does not ensure convergence, and existing analyses often req…
Fitted Q-Iteration via Max-Plus-Linear Approximation
In this study, we consider the application of max-plus-linear approximators for Q-function in offline reinforcement learning of discounted Markov decision processes. In particular, we incorporate these approximators to p…
Soft Fitted Q-Iteration without Bellman Completeness: Occupancy Reweighting and Temperature Annealing
Fitted \(Q\)-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability under function approximation often relies on Bellman completeness, which require…
Reinforcement Learning