Proceedings

Imitation Learning via Focused Satisficing

Rushit N. Shah, Nikolaos Agadakos, Synthia Sasulski, Ali Farajzadeh, Sanjiban Choudhury, Brian Ziebart

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 8768-8777.

https://doi.org/10.24963/ijcai.2025/975

Keywords

  • Robotics: ROB: Learning in robotics
  • Machine Learning: ML: Model-based and model learning reinforcement learning
  • Machine Learning: ML: Offline reinforcement learning
  • Uncertainty in AI: UAI: Sequential decision making

Abstract

Imitation learning often assumes that demonstrations are close to optimal according to some fixed, but unknown, cost function.

However, according to satisficing theory, humans often choose acceptable behavior based on their personal (and potentially dynamic) levels of aspiration, rather than achieving (near-) optimality. For example, a lunar lander demonstration that successfully lands without crashing might be acceptable to a novice despite being slow or jerky.

Using a margin-based objective to guide deep reinforcement learning, our focused satisficing approach to imitation learning seeks a policy that surpasses the demonstrator's aspiration levels---defined over trajectories or portions of trajectories---on unseen demonstrations without explicitly learning those aspirations. We show experimentally that this focuses the policy to imitate the highest quality (portions of) demonstrations better than existing imitation learning methods, providing much higher rates of guaranteed acceptability to the demonstrator, and competitive true returns on a range of environments.

Rushit N. Shah, Nikolaos Agadakos, Synthia Sasulski, Ali Farajzadeh, Sanjiban Choudhury, and Brian Ziebart. 2025. Imitation Learning via Focused Satisficing. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 8768–8777. https://doi.org/10.24963/ijcai.2025/975
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards