96
0
Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
attributed to: Hélène Plisnier, Denis Steckelmacher, Tim Brys, Diederik M. Roijers, Ann Nowé
Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and act safely around them. We argue that most current approaches that learn from human feedback are unsafe: rewarding or punishing the agent a-posteriori cannot immediately prevent it from wrong-doing. In this paper, we extend Policy Gradient to make it robust to external directives, that would otherwise break the fundamentally on-policy nature of Policy Gradient.
0
Vulnerabilities & Strengths