Context tree maximizing reinforcement learning
Recent developments in reinforcement learning for nonMarkovian problems witness a surge in history-based methods, among which we are particularly interested in two frameworks, ΦMDP and MC-AIXI-CTW. ΦMDP attempts to reduce the general RL problem, where the environment’s states and dynamics are both unknown, to an MDP, while MCAIXI-CTW incrementally learns a mixture of context trees as its environment model. The main idea of ΦMDP is to connect generic reinforcement learning with classical...[Show more]
|Collections||ANU Research Publications|
|Nguyen et al Context Tree Maximizing 2012.pdf||501.87 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.