Pseudorehearsal in value function approximation

Marochko, Vladimir; Johard, Leonard; Mazzara, Manuel

doi:10.48550/arxiv.1703.07075

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pseudo-rehearsal has also been applied to this problem by rehearsing randomly generated input items from basic distributions (e.g. uniform distribution) [35], [36], with a similar idea accomplished in actor-critic networks [37]. However, all these methods were applied to simple reinforcement tasks and did not utilise deep generative structures for generating pseudo-items or convolutional network architectures.…”

Section: Related Workmentioning

confidence: 99%

Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting

Atkinson,

McCane,

Szymanski

et al. 2018

Preprint

View full text Add to dashboard Cite

Neural networks can achieve extraordinary results on a wide variety of tasks. However, when they attempt to sequentially learn a number of tasks, they tend to learn the new task while destructively forgetting previous tasks. One solution to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of previous tasks. Our model combines pseudo-rehearsal with a deep generative model and a dual memory system, resulting in a method that does not demand additional storage requirements as the number of tasks increase. Our model iteratively learns three Atari 2600 games while retaining above human level performance on all three games and performing as well as a set of networks individually trained on the tasks. This result is achieved without revisiting or storing raw data from past tasks. Furthermore, previous state-of-the-art solutions demonstrate substantial forgetting compared to our model on these complex deep reinforcement learning tasks.

show abstract

Section: Related Workmentioning

confidence: 99%