Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating context, and enables online learning. However, RTRL's time and space complexity make it impractical. To overcome this problem, most recent work on RTRL focuses on approximation theories, while experiments are often limited to diagnostic settings. Here we explore the practical promise of RTRL in more realistic settings. We study actor-critic methods that combine RTRL and policy gradients, and test them in several subsets of DMLab-30, ProcGen, and Atari-2600 environments. On DMLab memory tasks, our system trained on fewer than 1.2 B environmental frames is competitive with or outperforms well-known IMPALA and R2D2 baselines trained on 10 B frames. To scale to such challenging tasks, we focus on certain well-known neural architectures with element-wise recurrence, allowing for tractable RTRL without approximation. We also discuss rarely addressed limitations of RTRL in real-world applications, such as its complexity in the multi-layer case.

翻译：实时循环学习（RTRL）用于序列处理循环神经网络（RNN）时，在概念上优于通过时间的反向传播（BPTT）。RTRL既不需要缓存历史激活值，也不需截断上下文，并且支持在线学习。然而，RTRL的时间和空间复杂度使其难以实用。为解决这一问题，近期大多数关于RTRL的研究聚焦于近似理论，而实验通常局限于诊断性设置。本文在更现实的场景中探索RTRL的实际潜力。我们研究了结合RTRL与策略梯度的演员-评论家方法，并在DMLab-30、ProcGen和Atari-2600环境的多个子集中进行测试。在DMLab记忆任务中，我们的系统在少于12亿环境帧的训练下，其表现与使用100亿帧训练的知名IMPALA和R2D2基线相当或更优。为扩展到此类挑战性任务，我们聚焦于某些具有逐元素循环特性的知名神经架构，从而在无需近似的情况下实现可处理的RTRL。我们还讨论了RTRL在实际应用中较少被提及的局限性，例如其多层情况下的复杂度。