Robust reinforcement learning agents using high-dimensional observations must be able to identify relevant state features amidst many exogeneous distractors. A representation that captures controllability identifies these state elements by determining what affects agent control. While methods such as inverse dynamics and mutual information capture controllability for a limited number of timesteps, capturing long-horizon elements remains a challenging problem. Myopic controllability can capture the moment right before an agent crashes into a wall, but not the control-relevance of the wall while the agent is still some distance away. To address this we introduce action-bisimulation encoding, a method inspired by the bisimulation invariance pseudometric, that extends single-step controllability with a recursive invariance constraint. By doing this, action-bisimulation learns a multi-step controllability metric that smoothly discounts distant state features that are relevant for control. We demonstrate that action-bisimulation pretraining on reward-free, uniformly random data improves sample efficiency in several environments, including a photorealistic 3D simulation domain, Habitat. Additionally, we provide theoretical analysis and qualitative results demonstrating the information captured by action-bisimulation.

翻译：鲁棒强化学习代理在使用高维观测时，必须能够从众多外部干扰因素中识别出相关的状态特征。能捕捉可控性的表征通过判断何种因素影响代理控制来识别这些状态元素。尽管逆动力学和互信息等方法能捕捉有限时间步内的可控性，但捕捉长期成分仍是一个具有挑战性的问题。短视的可控性虽能捕捉代理即将撞墙的瞬间，却无法在代理距离墙壁尚远时捕捉墙壁的控制相关性。为此，我们提出行动双模拟编码方法——一种受双模拟不变性伪度量启发的技术，通过递归不变性约束扩展单步可控性。通过这种方式，行动双模拟能学习多步可控性度量，平滑地衰减与控制相关的远距离状态特征。我们证明，在无奖励、均匀随机数据上对行动双模拟进行预训练能提升多个环境的样本效率，包括真实感三维模拟域Habitat。此外，我们通过理论分析和定性结果展示了行动双模拟所捕获的信息。