Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning

TL;DR

This paper introduces an incremental imitation-based method for safe reinforcement learning that avoids the pitfalls of surrogate constraint modifications, effectively improving safety and performance across various constrained RL benchmarks.

Contribution

The authors propose a novel approach that imitates good trajectories and avoids bad ones without modifying cost constraints, working from any initial policy.

Findings

Outperforms benchmark methods in expected cost reduction

Effectively manages CVaR cost constraints

Handles unknown cost constraints successfully

Abstract

A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or underestimation of the cost constraint at each state. Therefore, we provide an approach that does not modify the trajectory based cost constraint and instead imitates ``good'' trajectories and avoids ``bad'' trajectories generated from incrementally improving policies. We employ an oracle that utilizes a reward threshold (which is varied with learning) and the overall cost constraint to label trajectories as ``good'' or ``bad''. A key advantage of our approach is that we are able to work from any starting policy or set of trajectories and improve on it. In an exhaustive set of experiments, we demonstrate that our approach is able to outperform top benchmark approaches for solving Constrained RL problems, with respect to expected cost, CVaR cost, or even unknown cost constraints.