Reinforcement Learning with Long Short-Term Memory

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 relevant events. This is demonstrated in a T-maze task, as well as in a di cult variation of the pole balancing task.

• Type: Conference
• Year: 2001
• Where: NIPS
• Authors: Bram Bakker
• Keywords: NIPS 2001, NIPS 2007, Paper Presents Reinforcement, Pole Balancing Task, Recurrent Neural Network