Summary of On the Consistency Of Hyper-parameter Selection in Value-based Deep Reinforcement Learning, by Johan Obando-ceron et al.
On the consistency of hyper-parameter selection in value-based deep reinforcement learning
by Johan Obando-Ceron, João G.M. Araújo, Aaron Courville, Pablo Samuel Castro
First submitted to arxiv on: 25 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Deep reinforcement learning (deep RL) has achieved significant success in various domains through a combination of algorithmic design and careful selection of hyper-parameters. While algorithmic improvements often result from iterative enhancements built upon prior approaches, hyper-parameter choices are typically inherited from previous methods or fine-tuned specifically for the proposed technique. This paper conducts an extensive empirical study focusing on the reliability of hyper-parameter selection for value-based deep reinforcement learning agents. A new score is introduced to quantify the consistency and reliability of various hyper-parameters. The findings help establish which hyper-parameters are most critical to tune, as well as which tunings remain consistent across different training regimes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Deep RL has made big progress in many areas by combining clever algorithms with careful choices for certain numbers (hyper-parameters). These choices often depend on previous methods or the specific new technique. This study looks at how reliable these choices are for a type of deep RL called value-based agents. A new way to measure consistency is also introduced. The results help figure out which hyper-parameters matter most and which tunings work well across different training settings. |
Keywords
* Artificial intelligence * Reinforcement learning
