Episodic Reinforcement Learning by Logistic Reward-Weighted Regression
It has been a long-standing goal in the adaptive control community to reduce the generically difficult, general reinforcement learning (RL) problem to simpler problems solvable by supervised learning. While this approach is today’s standard for value function-based methods, fewer approaches are known that apply similar reductions to policy search methods. Recently, it has been shown that immediate RL problems can be solved by reward-weighted regression, and that the resulting algorithm is an expectation maximization (EM) algorithm with strong guarantees. In this paper, we extend this algorithm to the episodic case and show that it can be used in the context of LSTM recurrent neural networks (RNNs). The resulting RNN training algorithm is equivalent to a weighted self-modeling supervised learning technique. We focus on partially observable Markov decision problems (POMDPs) where it is essential that the policy is nonstationary in order to be optimal. We show that this new reward-weighted logistic regression used in conjunction with an RNN architecture can solve standard benchmark POMDPs with ease.
Unable to display preview. Download preview PDF.
- 1.Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial Intelligence 101 (1998)Google Scholar
- 5.Peters, J., Schaal, S.: Reinforcement learning by reward-weighted regression for operational space control. In: Proceedings of the International Conference on Machine Learning (ICML) (2007)Google Scholar
- 8.Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J.F. (eds.) A Field Guide to Dynamical Recurrent Neural Networks. IEEE Press, Los Alamitos (2001)Google Scholar
- 9.Schmidhuber, J.: RNN overview (2004), http://www.idsia.ch/~juergen/rnn.html
- 11.Chernoff, H., Moses, L.E.: Elementary Decision Theory. Dover Publications (1987)Google Scholar
- 13.James, M.R., Singh, S., Littman, M.L.: Planning with predictive state representations. In: Proceedings 2004 International Conference on Machine Learning and Applications, pp. 304–311 (2004)Google Scholar
- 15.Bakker, B.: Reinforcement learning with long short-term memory. In: Advances in Neural Information Processing Syst., vol. 14 (2002)Google Scholar