BIMRL: Brain Inspired Meta Reinforcement Learning
This work addresses sample efficiency for reinforcement learning agents, but it appears incremental as it builds on existing meta-RL approaches with brain-inspired modifications.
The paper tackles the problem of sample efficiency in reinforcement learning by introducing BIMRL, a brain-inspired meta-RL architecture with a novel memory module and intrinsic reward, which achieves competitive or superior performance compared to strong baselines on multiple MiniGrid environments.
Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt at formalizing and addressing this issue. Inspired by recent progress in meta-RL, we introduce BIMRL, a novel multi-layer architecture along with a novel brain-inspired memory module that will help agents quickly adapt to new tasks within a few episodes. We also utilize this memory module to design a novel intrinsic reward that will guide the agent's exploration. Our architecture is inspired by findings in cognitive neuroscience and is compatible with the knowledge on connectivity and functionality of different regions in the brain. We empirically validate the effectiveness of our proposed method by competing with or surpassing the performance of some strong baselines on multiple MiniGrid environments.