Policy Gradient Coagent Networks

Part of Advances in Neural Information Processing Systems 24 (NIPS 2011)

Bibtex Metadata Paper


Philip S. Thomas


We present a novel class of actor-critic algorithms for actors consisting of sets of interacting modules. We present, analyze theoretically, and empirically evaluate an update rule for each module, which requires only local information: the module's input, output, and the TD error broadcast by a critic. Such updates are necessary when computation of compatible features becomes prohibitively difficult and are also desirable to increase the biological plausibility of reinforcement learning methods.