# Two-Memory Reinforcement Learning

arXiv: https://arxiv.org/abs/2304.10098 · HTML: https://mlsanity.com/paper/2304.10098/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 12 of 12)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)
- [Episodic Memory Deep Q-Networks](https://mlsanity.com/paper/1805.07603/) (2018)
- [Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update](https://mlsanity.com/paper/1805.12375/) (2018)
- [Generalizable Episodic Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/2103.06469/) (2021)
- [Solving Continuous Control with Episodic Memory](https://mlsanity.com/paper/2106.08832/) (2021)
- [Event Tables for Efficient Experience Replay](https://mlsanity.com/paper/2211.00576/) (2022)
- [Continuous Episodic Control](https://mlsanity.com/paper/2211.15183/) (2022)

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

- [ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning](https://mlsanity.com/paper/2610.00592/) (2026)

## Abstract (arXiv)

While deep reinforcement learning has shown important empirical success, it tends to learn relatively slow due to slow propagation of rewards information and slow update of parametric neural networks. Non-parametric episodic memory, on the other hand, provides a faster learning alternative that does not require representation learning and uses maximum episodic return as state-action values for action selection. Episodic memory and reinforcement learning both have their own strengths and weaknesses. Notably, humans can leverage multiple memory systems concurrently during learning and benefit from all of them. In this work, we propose a method called Two-Memory reinforcement learning agent (2M) that combines episodic memory and reinforcement learning to distill both of their strengths. The 2M agent exploits the speed of the episodic memory part and the optimality and the generalization capacity of the reinforcement learning part to complement each other. Our experiments demonstrate that the 2M agent is more data efficient and outperforms both pure episodic memory and pure reinforcement learning, as well as a state-of-the-art memory-augmented RL agent. Moreover, the proposed approach provides a general framework that can be used to combine any episodic memory agent with other off-policy reinforcement learning algorithms.