CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning
This addresses the challenge of producing efficient and safe policies for robotic tasks like quadruped locomotion, which is incremental as it modifies existing RL methods rather than introducing a new paradigm.
The paper tackled the problem of enforcing hard constraints in deep reinforcement learning for legged locomotion, and the result was a novel algorithm called Constraints as Terminations (CaT) that achieved excellent constraint adherence on a real quadruped robot crossing obstacles.
Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient policies respecting hard constraints. In this work, we advocate for integrating constraints into robot learning and present Constraints as Terminations (CaT), a novel constrained RL algorithm. Departing from classical constrained RL formulations, we reformulate constraints through stochastic terminations during policy learning: any violation of a constraint triggers a probability of terminating potential future rewards the RL agent could attain. We propose an algorithmic approach to this formulation, by minimally modifying widely used off-the-shelf RL algorithms in robot learning (such as Proximal Policy Optimization). Our approach leads to excellent constraint adherence without introducing undue complexity and computational overhead, thus mitigating barriers to broader adoption. Through empirical evaluation on the real quadruped robot Solo crossing challenging obstacles, we demonstrate that CaT provides a compelling solution for incorporating constraints into RL frameworks. Videos and code are available at https://constraints-as-terminations.github.io.