Papers › Generalized Weighted Path Consistency for Mastering Atari Games

Generalized Weighted Path Consistency for Mastering Atari Games

21 Sep 2023NeurIPS 2023 11archive 2025-07-28

Reinforcement learning with the help of neural-guided search consumes huge computational resources to achieve remarkable performance. Path consistency (PC), i.e., f values on one optimal path should be identical, was previously imposed on MCTS by PCZero to improve the learning efficiency of AlphaZero. Not only PCZero still lacks a theoretical support but also considers merely board games. In this paper, PCZero is generalized into GW-PCZero for real applications with non-zero immediate reward. A weighting mechanism is introduced to reduce the variance caused by scouting's uncertainty on the f value estimation. For the first time, it is theoretically proved that neural-guided MCTS is guaranteed to find the optimal solution under the constraint of PC. Experiments are conducted on the Atari $100$k benchmark with $26$ games and GW-PCZero achieves 198% mean human performance, higher than the state-of-the-art EfficientZero's 194, while consuming only 25 of the computational resources consumed by EfficientZero.

PaperPDFCode

Code

cmach508/gw_pczero officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AlphaZero

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections