Assessing the Impact of Distribution Shift on Reinforcement Learning Performance

Research in machine learning is making progress in fixing its own reproducibility crisis. Reinforcement learning (RL), in particular, faces its own set of unique challenges. Comparison of point estimates, and plots that show successful convergence to the optimal policy during training, may obfuscate overfitting or dependence on the experimental setup. Although researchers in RL have proposed reliability metrics that account for uncertainty to better understand each algorithm's strengths and weaknesses, the recommendations of past work do not assume the presence …

challenges comparison convergence crisis cs.ai cs.lg cs.ma distribution experimental impact machine machine learning making overfitting performance plots policy progress reinforcement reinforcement learning reproducibility research set setup shift show training