Tackling Long-Horizon Tasks with Model-based Offline Reinforcement Learning

Model-based offline reinforcement learning (RL) is a compelling approach that addresses the challenge of learning from limited, static data by generating imaginary trajectories using learned models. However, it falls short in solving long-horizon tasks due to high bias in value estimation from model rollouts. In this paper, we introduce a novel model-based offline RL method, Lower Expectile Q-learning (LEQ), which enhances long-horizon task performance by mitigating the high bias in model-based value estimation via expectile regression of λ-returns. Our empirical results show that LEQ significantly outperforms previous model-based offline RL methods on long-horizon tasks, such as the D4RL AntMaze tasks, matching or surpassing the performance of model-free approaches. Our experiments demonstrate that expectile regression, λ-returns, and critic training on offline data are all crucial for addressing long-horizon tasks. Additionally, LEQ achieves performance comparable to the state-of-the-art model-based and model-free offline RL methods on the NeoRL benchmark and the D4RL MuJoCo Gym tasks.