Abstract | ||
---|---|---|
Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance of an actor-critic agent with neural-network based policy selection and function approximation in a pole balancing task and compare different pseudorehearsal approaches. We expect that pseudorehearsal assists learning even in such very simple problems, given proper initialization of the rehearsal parameters. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Artificial Intelligence | Forgetting,Function approximation,Computer science,Pole balancing,Artificial intelligence,Initialization,Machine learning,Reinforcement learning |
DocType | Volume | Citations |
Journal | abs/1704.04912 | 0 |
PageRank | References | Authors |
0.34 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vladimir Marochko | 1 | 0 | 0.34 |
Leonard Johard | 2 | 11 | 4.91 |
Manuel Mazzara | 3 | 493 | 64.05 |