Rémi Munos, Michal Valko, Yunhao Tang, Jean-Bastien Grill, Florent Altché, Thomas Hubert, Ioannis Antonoglou, Jean -Bastien
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The combination of Monte-Carlo tree search (MCTS) with deep reinforcement learning has led to significant advances in artificial intelligence. However, AlphaZero, the current stateof-the-art MCTS algorithm, still relies on handcrafted heuristics that are only partially understood. In this paper, we show that AlphaZero's search heuristics, along with other common ones such as UCT, are an approximation to the solution of a specific regularized policy optimization problem. With this insight, we propose a variant of AlphaZero which uses the exact solution to this policy optimization problem, and show experimentally that it reliably outperforms the original algorithm in multiple domains.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2007.12509")
get_code_for_paper("2007.12509")
have("2007.12509")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2007.12509.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2007.12509)
Connect an agent — have() is free.