Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains
This addresses the problem of scaling MARL in relational domains for researchers and practitioners, though it appears incremental as it combines existing techniques.
The paper tackles the challenges of sample inefficiency and poor generalization in multiagent reinforcement learning (MARL) by integrating relational planners with reinforcement learning, resulting in a sample-efficient approach that enables effective task transfer and generalization.
Multiagent Reinforcement Learning (MARL) poses significant challenges due to the exponential growth of state and action spaces and the non-stationary nature of multiagent environments. This results in notable sample inefficiency and hinders generalization across diverse tasks. The complexity is further pronounced in relational settings, where domain knowledge is crucial but often underutilized by existing MARL algorithms. To overcome these hurdles, we propose integrating relational planners as centralized controllers with efficient state abstractions and reinforcement learning. This approach proves to be sample-efficient and facilitates effective task transfer and generalization.