Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto, 2018 (MIT Press) - Introduces the foundational concepts of RL, including the agent-environment interface, states, actions, rewards, policies, and returns, defining the problem setup.
CS234: Reinforcement Learning (Spring 2024 Lecture 1: Introduction, The RL Problem), Emma Brunskill, 2024Stanford University Course Materials (Stanford Online (via YouTube)) - Offers a comprehensive academic introduction to the RL problem setup, describing agents, environments, states, actions, rewards, policies, and the concept of return within a structured course context.
Spinning Up in Deep RL: Key Concepts in RL, Joshua Achiam, 2018 (OpenAI) - A resource defining key RL concepts such as the agent-environment interface, states, actions, rewards, and policies, aiding practitioners in understanding the setup.
Dynamic Programming and Markov Processes, Ronald A. Howard, 1960 (MIT Press) - A seminal publication that introduces Markov Decision Processes, the mathematical framework for the reinforcement learning problem setup, discussing state transitions, actions, and optimal policies.