On the consistency of hyper-parameter selection in value-based deep reinforcement learning
This addresses the issue of overlooked hyper-parameter tuning in deep RL for researchers and practitioners, but it is incremental as it builds on existing methods without major algorithmic changes.
The paper tackles the problem of inconsistent hyper-parameter selection in value-based deep reinforcement learning by conducting an empirical study and introducing a new score to quantify reliability, finding which hyper-parameters are most critical and consistent across training regimes.
Deep reinforcement learning (deep RL) has achieved tremendous success on various domains through a combination of algorithmic design and careful selection of hyper-parameters. Algorithmic improvements are often the result of iterative enhancements built upon prior approaches, while hyper-parameter choices are typically inherited from previous methods or fine-tuned specifically for the proposed technique. Despite their crucial impact on performance, hyper-parameter choices are frequently overshadowed by algorithmic advancements. This paper conducts an extensive empirical study focusing on the reliability of hyper-parameter selection for value-based deep reinforcement learning agents, including the introduction of a new score to quantify the consistency and reliability of various hyper-parameters. Our findings not only help establish which hyper-parameters are most critical to tune, but also help clarify which tunings remain consistent across different training regimes.