Reinforcement Learning in Rich-Observation MDPs using Spectral Methods

  title={Reinforcement Learning in Rich-Observation MDPs using Spectral Methods},
  author={Kamyar Azizzadenesheli and Alessandro Lazaric and Animashree Anandkumar},
Designing effective exploration-exploitation algorithms in Markov decision processes (MDPs) with large state-action spaces is the main challenge in reinforcement learning (RL). In fact, the learning performance degrades with the number of states and actions in the MDP. However, MDPs often exhibit a low-dimensional latent structure in practice, where a small hidden state is observable through a possibly large number of observations. In this paper, we study the setting of rich-observation Markov… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 19 references

Similar Papers

Loading similar papers…