2 papers
cs.AI2021
Agent Incentives: A Causal Perspective
Tom Everitt, Ryan Carey, Eric Langlois +2
We present a framework for analysing agent incentives using causal influence diagrams. We establish that a well-known criterion for value of information is complete. We propose a n…
cs.AI2021
How RL Agents Behave When Their Actions Are Modified
Eric D. Langlois, Tom Everitt
Reinforcement learning in complex environments may require supervision to prevent the agent from attempting dangerous actions. As a result of supervisor intervention, the executed…