Extreme State Aggregation beyond MDPs
We consider a Reinforcement Learning setup without any (esp. MDP) assumptions on the environment. State aggregation and more generally feature reinforcement learning is concerned with mapping histories/raw-states to reduced/aggregated states. The idea behind both is that the resulting reduced process (approximately) forms a small stationary finite-state MDP, which can then be efficiently solved or learnt. We considerably generalize existing aggregation results by showing that even if the...[Show more]
|Collections||ANU Research Publications|
|Access Rights:||Open Access|
|Hutter Extreme State Aggregation 2014.pdf||204.89 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.