Planning with RL and episodic-memory behavioral priors
This work addresses the need for more efficient and interpretable learning algorithms in practical AI applications, though it appears incremental as it builds on existing behavioral prior methods.
The paper tackles the problem of sample inefficiency and lack of interpretability in reinforcement learning agents by using planning with episodic-memory behavioral priors, resulting in faster learning.
The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a better-than-random exploration policy or a safe-guard against the pitfalls of early learning. Existing solutions for imitation learning require a large number of expert demonstrations and rely on hard-to-interpret learning methods like Deep Q-learning. In this work we present a planning-based approach that can use these behavioral priors for effective exploration and learning in a reinforcement learning environment, and we demonstrate that curated exploration policies in the form of behavioral priors can help an agent learn faster.