A new advantage-weighted Bellman operator is claimed to speed up Q-learning convergence, but the proofs are flawed and experiments lack error bars.
A General Family of Robust Stochastic Operators for Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing on a sample path basis that our family of operators preserve optimality and increase the action gap. Our empirical results illustrate the strong benefits of our family of operators, significantly outperforming the classical Bellman operator and recently proposed operators.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Bellman operator convergence enhancements in reinforcement learning algorithms
A new advantage-weighted Bellman operator is claimed to speed up Q-learning convergence, but the proofs are flawed and experiments lack error bars.