Abstract
In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of behavior—such as ones which are deemed unsafe and to be avoided—are best captured through constraints. We propose a novel approach called First Order Constrained Optimization in Policy Space (FOCOPS) which maximizes an agent’s overall reward while ensuring the agent satisfies a set of cost constraints. Using data generated from the current policy, FOCOPS first finds the optimal update policy by solving a constrained optimization problem in the nonparameterized policy space. FOCOPS then projects the update policy back into the parametric policy space. Our approach has an approximate upper bound for worst-case constraint violation throughout training and is first-order in nature therefore simple to implement. We provide empirical evidence that our simple approach achieves better performance on a set of constrained robotics locomotive tasks.
Original language | English (US) |
---|---|
Journal | Advances in Neural Information Processing Systems |
Volume | 2020-December |
State | Published - 2020 |
Event | 34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online Duration: Dec 6 2020 → Dec 12 2020 |
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing