Mitigating Negative Side Effects via Environment Shaping
This addresses the issue of negative side effects in AI agents for users in unstructured environments, but it is incremental as it builds on existing human feedback methods.
The paper tackles the problem of agents causing negative side effects in unstructured environments by proposing a human-agent team framework where humans shape the environment to mitigate these effects without hindering the agent's task completion, and empirical evaluation shows the framework successfully mitigates side effects.
Agents operating in unstructured environments often produce negative side effects (NSE), which are difficult to identify at design time. While the agent can learn to mitigate the side effects from human feedback, such feedback is often expensive and the rate of learning is sensitive to the agent's state representation. We examine how humans can assist an agent, beyond providing feedback, and exploit their broader scope of knowledge to mitigate the impacts of NSE. We formulate this problem as a human-agent team with decoupled objectives. The agent optimizes its assigned task, during which its actions may produce NSE. The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task. We present an algorithm to solve this problem and analyze its theoretical properties. Through experiments with human subjects, we assess the willingness of users to perform minor environment modifications to mitigate the impacts of NSE. Empirical evaluation of our approach shows that the proposed framework can successfully mitigate NSE, without affecting the agent's ability to complete its assigned task.