This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari’s natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regression. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and Bradtke’s Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Empirical evaluations illustrate the effectiveness of our techniques in comparison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm.
|Publication status||Published - 1 Dec 2003|
|Event||"Planning for the Real World: The promises and challenges of dealing with uncertainty" @ NIPS 2003 - |
Duration: 8 Dec 2003 → 8 Dec 2003
|Conference||"Planning for the Real World: The promises and challenges of dealing with uncertainty" @ NIPS 2003|
|Period||8/12/03 → 8/12/03|