Reinforcement Learning with Long Short-Term Memory

Reinforcement Learning with Long Short-Term Memory (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Bram Bakker

Venue:	In NIPS
Citations:	29 - 3 self

BibTeX

@INPROCEEDINGS{Bakker02reinforcementlearning,
    author = {Bram Bakker},
    title = {Reinforcement Learning with Long Short-Term Memory},
    booktitle = {In NIPS},
    year = {2002},
    pages = {1475--1482},
    publisher = {MIT Press}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

This paper presents reinforcement learning with a Long ShortTerm Memory recurrent neural network: RL-LSTM. Model-free RL-LSTM using Advantage### learning and directed exploration can solve non-Markovian tasks with long-term dependencies between relevantevents. This is demonstrated in a T-maze task, as well as in a di#cult variation of the pole balancing task. 1

Citations

178	Long short-term memory - Hochreiter, Schmidhuber - 1997
173	Reinforcement learning with perceptual aliasing: The perceptual distinctions approach - Chrisman - 1992
77	Curious Model-Building Control Systems - Schmidhuber - 1991
70	Learning to use selective attention and short-term memory in sequential tasks - Mccallum - 1996
51	Learning to Forget: Continual Prediction with LSTM - Gers - 1999
42	Reinforcement learning with hidden states - Lin, Mitchell - 1993
17	Multi-player residual advantage learning with general function approximation (Tech - Harmon, Baird - 1996
8	Networks adjusting networks - Schmidhuber - 1990
1	Reinforcement learning with LSTM in non-Markovian tasks with longterm dependencies - Bakker - 2001
1	Using eligibility traces to #nd the best memoryless policy in Partially Observable Markov Decision Processes - Loch, Singh - 1998