Jan Peters

Parameterized Projected Bellman Operator

2023 · arXiv (Cornell University)

Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algorithms implement an iterated procedure where each step consists …

Velocity-History-Based Soft Actor-Critic Tackling IROS'24 Competition "AI Olympics with RealAIGym"

2024 · arXiv (Cornell University)

The ``AI Olympics with RealAIGym'' competition challenges participants to stabilize chaotic underactuated dynamical systems with advanced control algorithms. In this paper, we present a novel solution submitted to IROS'24 competition, which builds upon Soft Actor-Critic …