Artificial intelligence

Reinforcement learning

How agents learn by trial and error from rewards: environments, policies, value functions and the main algorithms.

Browse A–Z

Terms

55 terms

  • Thompson sampling

    Thompson sampling is a Bayesian strategy in reinforcement learning that picks each action by sampling from its posterior belief about the action's reward.

  • Trust region policy optimization TRPO

    Trust region policy optimization (TRPO) is a reinforcement learning algorithm that improves a policy while limiting each update with a KL divergence constraint.

  • Upper confidence bound UCB

    Upper confidence bound (UCB) is a reinforcement learning strategy that picks the action with the highest optimistic estimate of its reward.

  • Value function

    A value function in reinforcement learning estimates the expected discounted return an agent will collect from a state when it follows a given policy.

  • Value iteration

    Value iteration is a dynamic programming algorithm in reinforcement learning that repeatedly applies the Bellman optimality update to find an optimal policy.