Title | ||
---|---|---|
Prioritized Sweeping Neural DynaQ with Multiple Predecessors, and Hippocampal Replays. |
Abstract | ||
---|---|---|
During sleep and wakeful rest, the hippocampus replays sequences of place cells that have been activated during prior experiences. These replays have been interpreted as a memory consolidation process, but recent results suggest a possible interpretation in terms of reinforcement learning. The Dyna reinforcement learning algorithms use off-line replays to improve learning. Under limited replay budget, prioritized sweeping, which requires a model of the transitions to the predecessors, can be used to improve performance. We investigate if such algorithms can explain the experimentally observed replays. We propose a neural network version of prioritized sweeping Q-learning, for which we developed a growing multiple expert algorithm, able to cope with multiple predecessors. The resulting architecture is able to improve the learning of simulated agents confronted to a navigation task. We predict that, in animals, learning the transition and reward models should occur during rest periods, and that the corresponding replays should be shuffled. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-95972-6_4 | BIOMIMETIC AND BIOHYBRID SYSTEMS |
Keywords | DocType | Volume |
Reinforcement learning,Replays,DynaQ,Prioritized sweeping,Neural networks,Hippocampus,Navigation | Conference | 10928 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lise Aubin | 1 | 0 | 0.34 |
Khamassi Mehdi | 2 | 112 | 16.51 |
Girard Benoît | 3 | 185 | 22.20 |