# Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess

arXiv: https://arxiv.org/abs/2208.02029 · HTML: https://mlsanity.com/paper/2208.02029/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 3 Aug 2022.

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://mlsanity.com/paper/1701.01724/) (2017)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Deep Reinforcement Learning from Self-Play in Imperfect-Information Games](https://mlsanity.com/paper/1603.01121/) (2016)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [DREAM: Deep Regret minimization with Advantage baselines and Model-free learning](https://mlsanity.com/paper/2006.10410/) (2020)
- [Single Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1901.07621/) (2019)
- [Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess](https://mlsanity.com/paper/2110.01810/) (2021)
- [Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games](https://mlsanity.com/paper/1509.06731/) (2015)

## Built on by (most cited first, 3 of 3)

- [A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions](https://mlsanity.com/paper/2508.09128/) (2025)
- [Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chess](https://mlsanity.com/paper/2407.05864/) (2024)
- [Efficiently Training Neural Networks for Imperfect Information Games by Sampling Information Sets](https://mlsanity.com/paper/2407.05876/) (2024)

## Abstract (arXiv)

In this work, we adapt a training approach inspired by the original AlphaGo system to play the imperfect information game of Reconnaissance Blind Chess. Using only the observations instead of a full description of the game state, we first train a supervised agent on publicly available game records. Next, we increase the performance of the agent through self-play with the on-policy reinforcement learning algorithm Proximal Policy Optimization. We do not use any search to avoid problems caused by the partial observability of game states and only use the policy network to generate moves when playing. With this approach, we achieve an ELO of 1330 on the RBC leaderboard, which places our agent at position 27 at the time of this writing. We see that self-play significantly improves performance and that the agent plays acceptably well without search and without making assumptions about the true game state.