Abstract | ||
---|---|---|
We consider a new family of stochastic operators for reinforcement learning that seeks to alleviate negative effects and become more robust to approximation or estimation errors. Theoretical results are established, showing that our family of operators preserve optimality and increase the action gap in a stochastic sense. Empirical results illustrate the strong benefits of our robust stochastic operators, significantly outperforming the classical Bellman and recently proposed operators. |
Year | Venue | Keywords |
---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | reinforcement learning |
Field | DocType | Volume |
Computer science,Operator (computer programming),Artificial intelligence,Machine learning,Reinforcement learning | Conference | 32 |
ISSN | Citations | PageRank |
1049-5258 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
y. Lu | 1 | 180 | 20.18 |
Mark S. Squillante | 2 | 1366 | 157.28 |
Chai Wah Wu | 3 | 330 | 67.62 |