From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
This work addresses the need for flexible and accessible constraint representation in safe RL for practical applications, though it is incremental as it builds on existing methods by automating cost function design.
The paper tackles the problem of manually designing cost functions for safe reinforcement learning with natural language constraints by introducing the Trajectory-level Textual Constraints Translator (TTCT), which uses text as both constraint and training signal, resulting in policies with lower violation rates than standard methods.
Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessibility. Previous safe RL methods with natural language constraints typically need to design cost functions manually for each constraint, which requires domain expertise and lacks flexibility. In this paper, we harness the dual role of text in this task, using it not only to provide constraint but also as a training signal. We introduce the Trajectory-level Textual Constraints Translator (TTCT) to replace the manually designed cost function. Our empirical results demonstrate that TTCT effectively comprehends textual constraint and trajectory, and the policies trained by TTCT can achieve a lower violation rate than the standard cost function. Extra studies are conducted to demonstrate that the TTCT has zero-shot transfer capability to adapt to constraint-shift environments.