This famous paper gives a great review of the DQN algorithm a couple years after it changed everything in Deep RL. It compares six different extensions to DQN for Deep Reinforcement Learning, many of which have now become standard additions to DQN and other Deep RL algorithms. It also combines all of them together to produce the "rainbow" algorithm, which outperformed many other models for a while.

The phrase "ways of knowing" is fascinating and seems to have a particular meaning across multiple contexts.

I'd like to collect examples of its use and come up with a more concrete definition for Western audiences.

How close is it to the idea of ways (or methods) of learning and understanding? How is it bound up in the idea of pedagogy? How does it relate to orality and memory contrasted with literacy? Though it may not subsume the idea of scientific method, the use, evolution, and refinement of these methods over time may generally equate it with the scientific method.

Could such an oral package be considered a learning management system? How might we compare and contrast these for drawing potential equivalencies of these systems to put them on more equal footing from a variety of cultural perspectives? One is not necessarily better than another, but we should be able to better appreciate what each brings to the table of world knowledge.

The hermeneutic circle is the idea that understanding a text in whole is underpinned by understanding its constituent parts and understanding the individual parts is underpinned by understanding the whole thereby making a circle of understanding. This understanding of a text is going to be heavily influenced by a text's cultural, historical, literary, and other contexts.

Yang, Scott Cheng-Hsin, Chirag Rank, Jake Alden Whritner, Olfa Nasraoui, and Patrick Shafto. ‘Unifying Recommendation and Active Learning for Information Filtering and Recommender Systems’. Preprint. PsyArXiv, 25 August 2020. https://doi.org/10.31234/osf.io/jqa83.