Stable Dual Dynamic Programming
Tao Wang, Daniel Lizotte, Michael Bowling et al. · 2008
Recently, we have introduced a novel approach to dynamic programming and reinforcement learning that is based on maintaining explicit representations of stationary distributions instead of value functions. In this paper, we investigate the convergence properties of these dual algorithms both theoretically and empirically, and show how they can be scaled up by incorporating function approximation. 1
Cited by 24 works.
Authors
References
- Reinforcement Learning: An Introduction
- Dynamic Programming and Optimal Control
- Introduction to Reinforcement Learning
- Markov Decision Processes: Discrete Stochastic Dynamic Programming.
- Neuro-dynamic Programming
- An analysis of temporal-difference learning with function approximation
- Residual Algorithms: Reinforcement Learning with Function Approximation
- Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
- Generalization in Reinforcement Learning: Safely Approximating the Value Function
- On the Existence of Fixed Points for Approximate Value Iteration and Temporal-Difference Learning