Alec Koppel

On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation

2019 · arXiv (Cornell University)

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps to estimate the value function …

Approximate Equivariance in Reinforcement Learning

2024 · arXiv (Cornell University)

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is present, which makes imposing exact …