Summary of Cm-dqn: a Value-based Deep Reinforcement Learning Model to Simulate Confirmation Bias, by Jiacheng Shen et al.
CM-DQN: A Value-Based Deep Reinforcement Learning Model to Simulate Confirmation Bias
by Jiacheng Shen, Lihan Feng
First submitted to arxiv on: 10 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper proposes a new Deep Reinforcement Learning (DRL) algorithm called CM-DQN, which simulates human decision-making processes by applying different update strategies for positive and negative prediction errors. The algorithm is tested in two environments: Lunar Lander with continuous states and discrete actions, and a multi-armed bandit problem with discrete states and actions. The results show that confirmatory bias leads to better learning effects in both environments. CM-DQN applies the idea of confirmation bias to DRL, which can be used to improve decision-making processes in real-world applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how people make decisions when they’re wrong or right. Sometimes, we learn more from good outcomes and sometimes we learn more from bad ones. This paper proposes a new way for computers to learn like humans do. It’s called CM-DQN and it tries to mimic human decision-making by changing how the computer learns based on whether it’s correct or not. The researchers tested this algorithm in two different scenarios and found that when they simulated people being more influenced by good outcomes, the computer learned better. This could be useful for making decisions in real life. |
Keywords
* Artificial intelligence * Reinforcement learning
