2 papers
cs.LG2026
Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
Ilia Mahrooghi, Aryo Lotfi, Emmanuel Abbe
Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse rewards makes this process highly samp…
stat.ML2024
Multi-armed Bandits with Missing Outcome
Ilia Mahrooghi, Mahshad Moradi, Sina Akbari +1
While significant progress has been made in designing algorithms that minimize regret in online decision-making, real-world scenarios often introduce additional complexities, perha…