Tight Performance Bounds for Approximate Modified Policy Iteration with Non-Stationary Policies

Modified policy iteration algorithms for discounted Markov decision problems

Puterman, M. and Shin, M. (1978) · 1978

Earlier work this paper cites.

Markov decision processes: Discrete stochastic dynamic programming

Puterman, M. (1994) · 1994

Earlier work this paper cites.

An upper bound on the loss from approximate optimal-value functions

Original

Singh, S. and Yee, R. (1994) · 1994

Earlier work this paper cites.

Neuro-dynamic programming

Bertsekas, D. and Tsitsiklis, J. (1996) · 1996

Earlier work this paper cites.

On the Sample Complexity of Reinforcement Learning

Kakade, S. (2003) · 2003

Earlier work this paper cites.

Error bounds for approximate policy iteration

Munos, R. (2003) · 2003

Cited alongside, same era.

Value-iteration based fitted policy iteration: learning with a single trajectory

Antos, A., Szepesvarf, C., and Munos, R. (2007b) · 2007

Cited alongside, same era.

Performance bounds in L p {L}_{p} -norm for approximate value iteration

Munos, R. (2007) · 2007

Cited alongside, same era.

Error propagation for approximate policy and value iteration (extended version)

Farahmand, A., Munos, R., and Szepesvári, C. (2010) · 2010

Cited alongside, same era.

Fitted Q-iteration in continuous action-space MDPs

Antos, A., Munos, R., Szepesvari, C., et al

Cited in the paper.

Approximate modified policy iteration

Scherrer, B., Ghavamzadeh, M., Gabillon, V., and Geist, M. (2012a)

Cited in the paper.

Approximate modified policy iteration

Scherrer, B., Gabillon, V., Ghavamzadeh, M., and Geist, M. (2012b)

Cited in the paper.

Performance bound for approximate optimistic policy iteration

Scherrer, B. and Thiery, C. (2010) · 2010

Later among the works it cites.

Q-learning and enhanced policy iteration in discounted dynamic programming

Bertsekas, D. and Yu, H. (2012) · 2012

Later among the works it cites.

(Approximate) iterated successive approximations algorithm for sequential decision processes

Canbolat, P. and Rothblum, U. (2012) · 2012

Later among the works it cites.

On the use of non-stationary policies for stationary infinite-horizon markov decision processes

Scherrer, B. and Lesner, B. (2012) · 2012

Later among the works it cites.