2 Definition of Barycentric Interpolators
نویسنده
چکیده
In order to nd the optimal control of continuous state-space and time reinforcement learning (RL) problems, we approximate the value function (VF) with a particular class of functions called the barycentric interpolators. We establish su cient conditions under which a RL algorithm converges to the optimal VF, even when we use approximate models of the state dynamics and the reinforcement functions.
منابع مشابه
Barycentric Interpolators for Continuous Space and Time Reinforcement Learning
In order to find the optimal control of continuous state-space and time reinforcement learning (RL) problems, we approximate the value function (VF) with a particular class of functions called the barycentric interpolators. We establish sufficient conditions under which a RL algorithm converges to the optimal VF, even when we use approximate models of the state dynamics and the reinforcement fu...
متن کاملTowards Feature Selection In Actor-Critic Algorithms
Choosing features for the critic in actor-critic algorithms with function approximation is known to be a challenge. Too few critic features can lead to degeneracy of the actor gradient, and too many features may lead to slower convergence of the learner. In this paper, we show that a well-studied class of actor policies satisfy the known requirements for convergence when the actor features are ...
متن کاملBarycentric Subspaces Analysis on Spheres
This paper addresses the generalization of Principal Component Analysis (PCA) to Riemannian manifolds. Current methods like Principal Geodesic Analysis (PGA) and Geodesic PCA (GPCA) minimize the distance to a ”Geodesic subspace”. This allows to build sequences of nested subspaces which are consistent with a forward component analysis approach. However, these methods cannot easily be adapted to ...
متن کاملBarycentric Subspaces and Affine Spans in Manifolds
This paper addresses the generalization of Principal Component Analysis (PCA) to Riemannian manifolds. Current methods like Principal Geodesic Analysis (PGA) and Geodesic PCA (GPCA) minimize the distance to a ”Geodesic subspace”. This allows to build sequences of nested subspaces which are consistent with a forward component analysis approach. However, these methods cannot be adapted to a backw...
متن کاملInvariance of the barycentric subdivision of a simplicial complex
In this paper we prove that a simplicial complex is determined uniquely up to isomorphism by its barycentric subdivision as well as its comparability graph. We also put together several algebraic, combinatorial and topological invariants of simplicial complexes.
متن کامل