# Memory Augmented Self-Play

arXiv: https://arxiv.org/abs/1805.11016 · HTML: https://mlsanity.com/paper/1805.11016/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 1 of 1)

- [It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation](https://mlsanity.com/paper/2202.10608/) (2022)

## Abstract (arXiv)

Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the agent can store experience from the previous tasks. This enables the agent to come up with more diverse self-play tasks resulting in faster exploration of the environment. The agent pretrained in the memory augmented self-play setting easily outperforms the agent pretrained in no-memory self-play setting.