Skip to content

Reinforcement learning #5

Description

@justheuristic

Reinforcement learning

  • Theoretical bias
  • Planning and game trees
    Game tree approach to Pacman
  • Reinforcement learning, table-based Q-learning, Bellman equation.
    Stanford example with robot, pacman and gridworld.

Deep Reinforcement learning

  • Approximate reinforcement learning. Deep reinforcement learning. Caveats and pitfalls
    Playing atari with deep reinforcement learning.
  • POMDP and recurrent RL.
    Kung Fu and PBS cases: comparing DQN from previous seminar with DRQN.
  • [Sparse & delayed rewards. Hierarchical RL. Model-based Vs model-free options]?
    [Regular VS Hierarchical RL in Montezuma Revenge-like games]

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions