Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning
This work addresses the challenge of continual learning in reinforcement learning for researchers, though it appears incremental in nature.
The paper tackles the problem of training reinforcement learning agents in complex environments by introducing incremental learning, where optimal weight initialization from an easier environment leads to vastly superior results across ten specialized environments.
This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning method of incremental learning, where a challenging environment is solved using optimal weight initialization learned from first solving a similar easier environment. We show that incremental learning can produce vastly superior results than standard methods by providing a strong baseline method across ten Dex environments. We finally develop a saliency method for qualitative analysis of reinforcement learning, which shows the impact incremental learning has on network attention.