Mastering Memory Tasks with World Models
This addresses a key bottleneck in reinforcement learning for tasks requiring long-term memory and credit assignment, representing a strong incremental improvement over existing methods.
The paper tackles the problem of model-based reinforcement learning agents struggling with long-term dependencies by integrating state space models into world models to create Recall to Imagine (R2I), which achieves state-of-the-art performance on challenging memory tasks like BSuite and POPGym and superhuman performance in Memory Maze while maintaining comparable performance on classic RL tasks.
Current model-based reinforcement learning (MBRL) agents struggle with long-term dependencies. This limits their ability to effectively solve tasks involving extended time gaps between actions and outcomes, or tasks demanding the recalling of distant observations to inform current actions. To improve temporal coherence, we integrate a new family of state space models (SSMs) in world models of MBRL agents to present a new method, Recall to Imagine (R2I). This integration aims to enhance both long-term memory and long-horizon credit assignment. Through a diverse set of illustrative tasks, we systematically demonstrate that R2I not only establishes a new state-of-the-art for challenging memory and credit assignment RL tasks, such as BSuite and POPGym, but also showcases superhuman performance in the complex memory domain of Memory Maze. At the same time, it upholds comparable performance in classic RL tasks, such as Atari and DMC, suggesting the generality of our method. We also show that R2I is faster than the state-of-the-art MBRL method, DreamerV3, resulting in faster wall-time convergence.