Deep Reinforcement Learning

By Yuxi Li. 2018

137 citations recorded by the source corpus.

We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details. We discuss six core elements, six important mechanisms, and twelve applications, focusing on contemporary work, and in historical contexts. We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources. Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation. Then we discuss important mechanisms for RL, including attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn. After that, we discuss RL applications, including games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art. Finally we summarize briefly, discuss challenges and opportunities, and close with an epilogue.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chao Yu
2. Jiming Liu
3. Shamim Nemati
4. Klaus-Jürgen Diepold
5. Seth D. Baum
6. Sven Gronauer
7. Guoqi Ren

In Control and Systems Engineering

1. Shamim Nemati
2. Klaus-Jürgen Diepold
3. Seth D. Baum
4. Sven Gronauer
5. Chao Yu
6. Jiming Liu

Citations in the corpus

• Reinforcement Learning in Healthcare: A Survey (2019, methodology): “There has been a significant achievement in the continuous control using AC [74] and PS meth-ods [42] in the past few years, particularly from the area of robotic control and DRL.”
• Explainable Reinforcement Learning: A Survey (2020, unknown): “ll then learn a policy, i.e., an action-staterelation, in order to maximize the cumulative reward and be able to select the most optimal action in each situation. For more information on RL, see also [53, 34]. 1.3 Definition of important terms As already mentioned in section 1, the more complex a sys”
• Neural Approaches to Conversational AI (2018, unknown): “ readers are referred to existing textbooks and reviews, such as Sutton and Barto (2018); Kaelbling et al. (1996); Bertsekas and Tsitsiklis (1996); Szepesvari´ (2010); Wiering and van Otterlo (2012); Li (2018). 4Similar to DSSM, seq2seq can be applied to a variety of generation tasks depending on th”
• Multi-agent deep reinforcement learning: a survey (2021, background): “We refer the interested reader for an overview of those topics to the articles of Arulkumaran et al. (2017) and Li (2018).”
• A Survey of Artificial General Intelligence Projects for Ethics, Risk, and Policy (2017, result): “2015; Steunebrink et al. 2016).10 Other projects focus on safety issues in near-term AI in the context of robotics (FLOWERS; Oudeyer et al. 2011) and reinforcement learning (DeepMind and OpenAI; Christiano et al. 2017), the latter being consistent with an agenda of using near-term AI to study long-t”