# Distilling Reinforcement Learning Tricks for Video Games

arXiv: https://arxiv.org/abs/2107.00703 · HTML: https://mlsanity.com/paper/2107.00703/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 13 of 13)

- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [Playing FPS Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05521/) (2016)
- [ViZDoom Competitions: Playing Doom from Pixels](https://mlsanity.com/paper/1809.03470/) (2018)
- [Action Space Shaping in Deep Reinforcement Learning](https://mlsanity.com/paper/2004.00980/) (2020)
- [Augmenting Automated Game Testing with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.15819/) (2021)
- [Learning to Act by Predicting the Future](https://mlsanity.com/paper/1611.01779/) (2016)
- [Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution](https://mlsanity.com/paper/2009.14108/) (2020)
- [The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors](https://mlsanity.com/paper/1904.10079/) (2019)
- [Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning](https://mlsanity.com/paper/2003.05012/) (2020)
- [Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations](https://mlsanity.com/paper/2006.09939/) (2020)

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

- [MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned](https://mlsanity.com/paper/2202.10583/) (2022)
- [Meta-Learning Strategies through Value Maximization in Neural Networks](https://mlsanity.com/paper/2310.19919/) (2023)
- [Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments](https://mlsanity.com/paper/2310.10170/) (2023)

## Abstract (arXiv)

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering steps ("tricks") which may be needed to effectively use RL, such as reward shaping, curriculum learning, and splitting a large task into smaller chunks. Such tricks are common, if not necessary, to achieve state-of-the-art results and win RL competitions. To ease the engineering efforts, we distill descriptions of tricks from state-of-the-art results and study how well these tricks can improve a standard deep Q-learning agent. The long-term goal of this work is to enable combining proven RL methods with domain-specific tricks by providing a unified software framework and accompanying insights in multiple domains.