Skip to content

Latest commit

 

History

History
9 lines (6 loc) · 1 KB

PGS.md

File metadata and controls

9 lines (6 loc) · 1 KB

Policy Gradient Search: Online Planning and Expert Iteration without Search Trees

Thomas Anthony, Robert Nishihara, Philipp Moritz, Tim Salimans, and John Schulman

Abstract

Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play.

MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the values of states with Monte Carlo averages, stored in a search tree; this does not scale to games with very high branching factors.

We propose an alternative simulation-based search method, Policy Gradient Search (PGS), which adapts a neural network simulation policy online via policy gradient updates, avoiding the need for a search tree. In Hex, PGS achieves comparable performance to MCTS, and an agent trained using Expert Iteration with PGS was able defeat MoHex 2.0, the strongest open-source Hex agent, in 9x9 Hex.