An Online Prediction Algorithm For Reinforcement Learning With Linear Function Approximation Using Cross Entropy Method

Abstract

In this paper, we provide two new stable online algorithms for the problem of prediction in reinforcement learning, *i.e.*, estimating the value function of a model-free Markov reward process using the linear function approximation architecture and with memory and computation costs scaling quadratically in the size of the feature set. The algorithms employ the multi-timescale stochastic approximation variant of the very popular cross entropy (CE) optimization method which is a model based search method to find the global optimum of a real-valued function. A proof of convergence of the algorithms using the ODE method is provided. We supplement our theoretical results with experimental comparisons. The algorithms achieve good performance fairly consistently on many RL benchmark problems with regards to computational efficiency, accuracy and stability.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyjoseph2018an

Related papers

• Improved Regret For Efficient Online Reinforcement Learning With Linear Function Approximation (2023)0.00
• Adapting The Function Approximation Architecture In Online Reinforcement Learning (2021)0.00
• Nearly Minimax Optimal Offline Reinforcement Learning With Linear Function Approximation: Single-agent MDP And Markov Game (2022)0.00
• Distributionally Robust Online Markov Game With Linear Function Approximation (2025)0.00
• Reward-free Model-based Reinforcement Learning With Linear Function Approximation (2021)0.00
• Distributionally Robust Offline Reinforcement Learning With Linear Function Approximation (2022)0.00
• Provably Efficient Reinforcement Learning With Linear Function Approximation (2019)11.76
• Uniform-pac Bounds For Reinforcement Learning With Linear Function Approximation (2021)0.00