A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimization
This provides theoretical guarantees for imitation learning in multi-objective optimization, which is incremental as it extends existing methods to new settings.
The paper proves that Wasserstein inverse reinforcement learning enables the learner's reward values to imitate the expert's in finite iterations for multi-objective optimization, and also proves it enables imitation of optimal solutions with lexicographic order.
We prove Wasserstein inverse reinforcement learning enables the learner's reward values to imitate the expert's reward values in a finite iteration for multi-objective optimizations. Moreover, we prove Wasserstein inverse reinforcement learning enables the learner's optimal solutions to imitate the expert's optimal solutions for multi-objective optimizations with lexicographic order.