# Final Adaptation Reinforcement Learning for N-Player Games

arXiv: https://arxiv.org/abs/2111.14375 · HTML: https://mlsanity.com/paper/2111.14375/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 29 Nov 2021.

## Builds on (most cited first, 3 of 3)

- [Ludii -- The Ludemic General Game System](https://mlsanity.com/paper/1905.05013/) (2019)
- [Mastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping](https://mlsanity.com/paper/1604.05085/) (2016)
- [General Board Game Playing for Education and Research in Generic AI Game Learning](https://mlsanity.com/paper/1907.06508/) (2019)

## Built on by (most cited first, 2 of 2)

- [AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time](https://mlsanity.com/paper/2204.13307/) (2022)
- [Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning](https://mlsanity.com/paper/2301.12167/) (2023)

## Abstract (arXiv)

This paper covers n-tuple-based reinforcement learning (RL) algorithms for games. We present new algorithms for TD-, SARSA- and Q-learning which work seamlessly on various games with arbitrary number of players. This is achieved by taking a player-centered view where each player propagates his/her rewards back to previous rounds. We add a new element called Final Adaptation RL (FARL) to all these algorithms. Our main contribution is that FARL is a vitally important ingredient to achieve success with the player-centered view in various games. We report results on seven board games with 1, 2 and 3 players, including Othello, ConnectFour and Hex. In most cases it is found that FARL is important to learn a near-perfect playing strategy. All algorithms are available in the GBG framework on GitHub.