Keywords: Reinforcement Learning, Generalization
Abstract: Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-stationary behaviour policy. Due to the transience of this non-stationarity, it is often not explicitly addressed in deep RL and a single neural network is continually updated. However, we find evidence that neural networks exhibit a memory effect, where these transient non-stationarities can permanently impact the latent representation and adversely affect generalisation performance. Consequently, to improve generalisation of deep RL agents, we propose Iterated Relearning (ITER). ITER augments standard RL training by repeated knowledge transfer of the current policy into a freshly initialised network, which thereby experiences less non-stationarity during training. Experimentally, we show that ITER improves performance on the challenging generalisation benchmarks ProcGen and Multiroom.
One-sentence Summary: We find that transient non-stationarity can worsen generalization in reinforcement learning and propose a method to overcome this effeect.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Supplementary Material: zip
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [ProcGen](https://paperswithcode.com/dataset/procgen)