Multi-task learning with deep model based reinforcement learning
This addresses the open problem of multi-task reinforcement learning for AI researchers, offering a novel method that enhances learning efficiency across tasks.
The paper tackles multi-task reinforcement learning by introducing a model-based deep reinforcement learning approach that benefits from learning multiple tasks simultaneously, showing improved performance without degradation.
In recent years, model-free methods that use deep learning have achieved great success in many different reinforcement learning environments. Most successful approaches focus on solving a single task, while multi-task reinforcement learning remains an open problem. In this paper, we present a model based approach to deep reinforcement learning which we use to solve different tasks simultaneously. We show that our approach not only does not degrade but actually benefits from learning multiple tasks. For our model, we also present a new kind of recurrent neural network inspired by residual networks that decouples memory from computation allowing to model complex environments that do not require lots of memory.