Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective
This work addresses the problem of transferring learned policies from simulation to real robots for researchers and practitioners in robotics and reinforcement learning, representing an incremental improvement over existing methods.
The paper tackles the sim-to-real gap in reinforcement learning for robotic control by formulating it as an information bottleneck problem and proposing the Historical Information Bottleneck (HIB) method, which learns privileged knowledge representations from historical trajectories to improve generalizability in both simulated and real-world tasks.
Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that these methods are limited in their ability to fully leverage the available privileged knowledge, resulting in suboptimal performance. In this paper, we formulate the sim-to-real gap as an information bottleneck problem and therefore propose a novel privileged knowledge distillation method called the Historical Information Bottleneck (HIB). In particular, HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Theoretical analysis shows that the learned privileged knowledge representation helps reduce the value discrepancy between the oracle and learned policies. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods. Videos of real-world experiments are available at https://sites.google.com/view/history-ib .