Curriculum Design for Teaching via Demonstrations: Theory and Applications
This addresses the challenge of efficient teaching via demonstrations for AI agents, though it is incremental as it builds on existing learner models like MaxEnt-IRL and CrossEnt-BC.
The paper tackles the problem of designing personalized curricula over demonstrations to accelerate learner convergence in sequential decision-making, showing that their unified strategy achieves similar convergence guarantees without requiring access to the learner's internal dynamics.
We consider the problem of teaching via demonstrations in sequential decision-making settings. In particular, we study how to design a personalized curriculum over demonstrations to speed up the learner's convergence. We provide a unified curriculum strategy for two popular learner models: Maximum Causal Entropy Inverse Reinforcement Learning (MaxEnt-IRL) and Cross-Entropy Behavioral Cloning (CrossEnt-BC). Our unified strategy induces a ranking over demonstrations based on a notion of difficulty scores computed w.r.t. the teacher's optimal policy and the learner's current policy. Compared to the state of the art, our strategy doesn't require access to the learner's internal dynamics and still enjoys similar convergence guarantees under mild technical conditions. Furthermore, we adapt our curriculum strategy to the setting where no teacher agent is present using task-specific difficulty scores. Experiments on a synthetic car driving environment and navigation-based environments demonstrate the effectiveness of our curriculum strategy.