# Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting

Source: [Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting](<https://www.sota2.com/research/paper/68fa68ef1e209131cea1f0b0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:48:52.480Z

Authors: Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins

Published: 2018-12-06T11:20:18.000Z

## Abstract

Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophically forgetting previous ones. We propose a model that overcomes catastrophic forgetting in sequential reinforcement learning by combining ideas from continual learning in both the image classification domain and the reinforcement learning domain. This model features a dual memory system which separates continual learning from reinforcement learning and a pseudo-rehearsal system that "recalls" items representative of previous tasks via a deep generative network. Our model sequentially learns Atari 2600 games without demonstrating catastrophic forgetting and continues to perform above human level on all three games. This result is achieved without: demanding additional storage requirements as the number of tasks increases, storing raw data or revisiting past tasks. In comparison, previous state-of-the-art solutions are substantially more vulnerable to forgetting on these complex deep reinforcement learning tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1812.02464>)

[PDF](<https://arxiv.org/pdf/1812.02464.pdf>)
