Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess
This addresses the problem of efficient decision-making in complex games with hidden information for AI researchers and game developers, representing a strong specific advance rather than a broad paradigm shift.
The paper tackles the challenge of planning in large imperfect information games by introducing deep synoptic Monte Carlo planning (DSMCP), which uses a belief state and synopses for uncertainty handling, resulting in Penumbra winning the 2020 reconnaissance blind chess competition against 33 other programs.
This paper introduces deep synoptic Monte Carlo planning (DSMCP) for large imperfect information games. The algorithm constructs a belief state with an unweighted particle filter and plans via playouts that start at samples drawn from the belief state. The algorithm accounts for uncertainty by performing inference on "synopses," a novel stochastic abstraction of information states. DSMCP is the basis of the program Penumbra, which won the official 2020 reconnaissance blind chess competition versus 33 other programs. This paper also evaluates algorithm variants that incorporate caution, paranoia, and a novel bandit algorithm. Furthermore, it audits the synopsis features used in Penumbra with per-bit saliency statistics.