Abstract | ||
---|---|---|
Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation. We tested agent in a pole balancing task and compared different pseudorehearsal approaches. We have found that pseudorehearsal can assist learning and decrease forgetting. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/AINA.2018.00099 | 2018 IEEE 32nd International Conference on Advanced Information Networking and Applications (AINA) |
Keywords | DocType | Volume |
reinforcement learning,neural networks,catastrophic forgetting,pseudorehearsal | Conference | abs/1712.07686 |
ISSN | ISBN | Citations |
1550-445X | 978-1-5386-2196-7 | 1 |
PageRank | References | Authors |
0.37 | 11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vladimir Marochko | 1 | 1 | 0.37 |
Leonard Johard | 2 | 11 | 4.91 |
Manuel Mazzara | 3 | 493 | 64.05 |
Luca Longo | 4 | 1 | 0.37 |