Curiosity-Driven Exploration via Latent Bayesian Surprise
This addresses the challenge of efficient exploration in reinforcement learning for continuous tasks and video games, though it appears incremental as it builds on existing Bayesian surprise approaches.
The paper tackles the problem of enabling more natural exploration in reinforcement learning by proposing a computationally cheap method that applies Bayesian surprise in a latent space, showing positive comparisons with state-of-the-art methods and resilience to environmental stochasticity.
The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement Learning, with more natural exploration capabilities. A promising approach in this respect has consisted of using Bayesian surprise on model parameters, i.e. a metric for the difference between prior and posterior beliefs, to favour exploration. In this contribution, we propose to apply Bayesian surprise in a latent space representing the agent's current understanding of the dynamics of the system, drastically reducing the computational costs. We extensively evaluate our method by measuring the agent's performance in terms of environment exploration, for continuous tasks, and looking at the game scores achieved, for video games. Our model is computationally cheap and compares positively with current state-of-the-art methods on several problems. We also investigate the effects caused by stochasticity in the environment, which is often a failure case for curiosity-driven agents. In this regime, the results suggest that our approach is resilient to stochastic transitions.