Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
For researchers in multitask RL, this work challenges the necessity of planning and highlights representation learning as a simpler, more scalable alternative.
The authors argue that representation learning, not model-based planning, is the key to scalable multitask reinforcement learning. Their model-free algorithm MR.Q with predictive auxiliary objectives outperforms world-model-based methods and baselines across diverse continuous control tasks, reducing computational overhead and improving wall-clock efficiency.
Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability. We revisit this question and argue that the primary driver of scalable multitask RL is not model-based control, but \emph{representation learning}. In particular, we show that combining predictive, model-based representations with high-capacity value function approximation is sufficient to achieve strong performance, even without planning. We evaluate a simple model-free algorithm, MR.Q, coupled with auxiliary predictive objectives into a scalable actor-critic architecture. This approach outperforms a recent world-model-based method and a range of deep RL baselines across a diverse suite of multitask continuous control tasks, while significantly reducing computational overhead and improving wall-clock efficiency. We observe consistent improvements with increased model capacity and show through ablations that predictive representation learning is critical for performance.