Wikipedia

User:ZachsGenericUsername/sandbox/Deep reinforcement learning

This is an old revision of this page, as edited by ZachsGenericUsername (talk | contribs) at 23:34, 29 October 2020. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Deep reinforcement learning is a machine learning method that takes principles from both reinforcement learning and deep learning to obtain benefits from both. Deep reinforcement learning has a huge diversity of applications from video games and computer science to healthcare and finance because of how powerful it is as a machine learning technique. Games in particular have been extremely influential in the development of reinforcement learning algorithms because of the ease of access of input and output variables which leads to quick testing.

Example Applications

Deep reinforcement learning has become very influential in many areas and has gained a diverse variety of applications, some of which include:

  • Deep Q networks, or learning algorithms without a specified model that analyze a situation and produce an action the agent should take.
  • The AlphaZero algorithm, developed by DeepMind, that has achieved super-human like performance in many games.
  • Image enhance models such as GAN and Unet which have attained much higher performance compared to the previous methods such as super-resolution and segmentation[1]
  • Procedural level generation in video games [2]

Generalization

One thing deep reinforcement learning excels at is generalization, or the ability to use one machine learning model for multiple tasks.

When using reinforcement learning, the model must be aware of its environment which is usually provided manually but when this is combined with deep learning, which is very good at dictating features from raw data (e.g. pixels or raw image files) the algorithm gets the benefits of reinforcement learning without being told what it's environment looks like. With this layer of abstraction, deep reinforcement learning algorithms can become generalized and the same model can be used for different tasks. Automatic feature extraction can provide much better accuracy than if a human to do this job[3]


References

  1. ^ Deep reinforcement learning fundamentals, research and applications. Dong, Hao., Ding, Zihan., Zhang, Shanghang. Singapore: Springer. 2020. ISBN 978-981-15-4095-0. OCLC 1163522253.{{cite book}}: CS1 maint: others (link)
  2. ^ "Fix me :(". ucsb-primo.hosted.exlibrisgroup.com. Retrieved 2020-10-29.{{cite web}}: CS1 maint: url-status (link)
  3. ^ "https://ucsb-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_proquest2074058918&vid=UCSB&search_scope=default_scope&tab=default_tab&lang=en_US&context=PC". ucsb-primo.hosted.exlibrisgroup.com. Retrieved 2020-10-22. {{cite web}}: External link in |title= (help)
Retrieved from "https://en.wikipedia.org/w/index.php?title=User:ZachsGenericUsername/sandbox/Deep_reinforcement_learning&oldid=986127670"