Now showing items 1-1 of 1

    • Exploration in Gradient-Based Reinforcement Learning 

      Meuleau, Nicolas; Peshkin, Leonid; Kim, Kee-Eung (2001-04-03)
      Gradient-based policy search is an alternative to value-function-based methods for reinforcement learning in non-Markovian domains. One apparent drawback of policy search is its requirement that all actions be 'on-policy'; ...