Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we found that surprisingly, reward prediction is often a bottleneck of MBRL, especially for sparse rewards that are challenging (or even ambiguous) to predict. Motivated by the intuition that humans can learn from rough reward estimates, we propose a simple yet effective reward smoothing approach, DreamSmooth, which learns to predict a temporally-smoothed reward, instead of the exact reward at the given timestep. We empirically show that DreamSmooth achieves state-of-the-art performance on long-horizon sparse-reward tasks both in sample efficiency and final performance without losing performance on common benchmarks, such as Deepmind Control Suite and Atari benchmarks.

翻译：基于模型的强化学习（MBRL）因其能够以样本高效的方式学习复杂行为而备受关注：通过生成带有预测奖励的想象轨迹来规划动作。尽管取得了成功，但我们发现，奖励预测常常是MBRL的一个瓶颈，尤其是在预测稀疏奖励（这具有挑战性甚至模糊性）时。受人类能从粗略奖励估计中学习的直觉启发，我们提出了一种简单而有效的奖励平滑方法DreamSmooth，该方法学习预测一个时间上的平滑奖励，而不是给定时间步上的精确奖励。我们通过实验证明，DreamSmooth在长时域稀疏奖励任务上，无论在样本效率还是最终性能方面都达到了最先进的水平，且在常见基准（如Deepmind Control Suite和Atari基准）上并未降低性能。