Reinforcement Learning from Delayed Observations via World Models

arXiv:2403.12309v1 Announce Type: new
Abstract: In standard Reinforcement Learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constraints and can significantly impact the performance of RL algorithms. In this paper, we focus on addressing observation delays in partially observable environments. We propose leveraging world models, which have shown success in integrating past observations and learning dynamics, to handle observation delays. By …

abstract agents algorithms arxiv constraints cs.ai cs.lg effects feedback focus however impact paper performance practice reinforcement reinforcement learning standard them true type via world world models