Reinforcement Learning through Active Inference
This work addresses a fundamental challenge in reinforcement learning for AI researchers, offering a new approach that integrates insights from neuroscience.
The paper tackled the problem of balancing exploration and exploitation in reinforcement learning by proposing a novel objective inspired by active inference, resulting in an algorithm that achieved robust performance on challenging benchmarks with various reward types.
The central tenet of reinforcement learning (RL) is that agents seek to maximize the sum of cumulative rewards. In contrast, active inference, an emerging framework within cognitive and computational neuroscience, proposes that agents act to maximize the evidence for a biased generative model. Here, we illustrate how ideas from active inference can augment traditional RL approaches by (i) furnishing an inherent balance of exploration and exploitation, and (ii) providing a more flexible conceptualization of reward. Inspired by active inference, we develop and implement a novel objective for decision making, which we term the free energy of the expected future. We demonstrate that the resulting algorithm successfully balances exploration and exploitation, simultaneously achieving robust performance on several challenging RL benchmarks with sparse, well-shaped, and no rewards.