mlsanityData to 14 Oct 2026

Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess

arXiv 2110.01810 ↗First posted 5 Oct 2021cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 25 of its 67 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

25 of 67 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  5. 2018Sanity Checks for Saliency Mapscited by 1,156
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  7. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  8. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  9. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  10. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 233
  11. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 158
  12. 2019XRAI: Better Attributions Through Regionscited by 116
13 more
  1. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 114
  2. 2018Deep Counterfactual Regret Minimizationcited by 103
  3. 2019On the Limitations of Representing Functions on Setscited by 90
  4. 2014Algorithms for multi-armed bandit problemscited by 64
  5. 2019Accelerating Self-Play Learning in Gocited by 64
  6. 2019ELF OpenGo: An Analysis and Open Reimplementation of AlphaZerocited by 39
  7. 2020Corralling Stochastic Bandit Algorithmscited by 23
  8. 2019DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPscited by 21
  9. 2019To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributionscited by 20
  10. 2020Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chesscited by 15
  11. 2020Measuring and Harnessing Transference in Multi-Task Learningcited by 11
  12. 2014Computing Approximate Nash Equilibria and Robust Best-Responses Using Samplingcited by 6
  13. 2018On the Complexity of Reconnaissance Blind Chesscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 1.

4 papers.

  1. 2022Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chesscited by 3
  2. 2022Towards Using Fully Observable Policies for POMDPscited by 1
  3. 2024Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chesscited by 1
  4. 2025Adaptive Bias Generalized Rollout Policy Adaptation on the Flexible Job-Shop Scheduling Problemcited by 0