This paper introduces BarlowRL, a data-efficient reinforcement learning agent
that combines the Barlow Twins self-supervised learning framework with DER
(Data-Efficient Rainbow) algorithm. BarlowRL outperforms both DER and its
contrastive counterpart CURL on the Atari 100k benchmark. BarlowRL avoids
dimensional collapse by enforcing information spread to the whole space. This
helps RL algorithms to utilize uniformly spread state representation that
eventually results in a remarkable performance. The integration of Barlow Twins
with DER enhances data efficiency and achieves superior performance in the RL
tasks. BarlowRL demonstrates the potential of incorporating self-supervised
learning techniques to improve RL algorithms.

BarlowRL 结合 Barlow Twins 自监督学习框架与 DER 算法，是一种高效利用数据的强化学习代理，在 Atari 100k 基准测试中表现优于 DER 和其对比算法 CURL。BarlowRL 通过在整个空间内强制信息传播来避免维度趋于坍缩，帮助 RL 算法利用均匀分布的状态表示，从而取得显著的性能提高。结合 Barlow Twins 与 DER 实现了数据效率的提升，并在 RL 任务中取得了卓越的性能，展示了将自监督学习技术整合到改进 RL 算法中的潜力。