Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties

TL;DR

This paper introduces an augmented state and reward penalty approach to solve constrained reinforcement learning problems, effectively handling expected cost constraints and outperforming existing methods on benchmarks.

Contribution

It presents a novel unconstrained formulation with state augmentation and reward penalties, offering a new paradigm for constrained RL solutions.

Findings

Outperforms leading approaches on benchmark problems

Provides a general and theoretically sound formulation

Effectively manages expected cost constraints

Abstract

Constrained Reinforcement Learning has been employed to enforce safety constraints on policy through the use of expected cost constraints. The key challenge is in handling expected cost accumulated using the policy and not just in a single step. Existing methods have developed innovative ways of converting this cost constraint over entire policy to constraints over local decisions (at each time step). While such approaches have provided good solutions with regards to objective, they can either be overly aggressive or conservative with respect to costs. This is owing to use of estimates for "future" or "backward" costs in local cost constraints. To that end, we provide an equivalent unconstrained formulation to constrained RL that has an augmented state space and reward penalties. This intuitive formulation is general and has interesting theoretical properties. More importantly, this provides a new paradigm for solving constrained RL problems effectively. As we show in our experimental results, we are able to outperform leading approaches on multiple benchmark problems from literature.