This is a bit of vague question. It would be helpful to understand the context of the problems you're interested in solving. It would also be helpful to get a sense of your math and coding background.
If you curious about the space in general and looking to get started, checkout OpenAI's Spinning up in Deep RL tutorials. They start from the foundations and work up to implementing standard policy optimization algorithms for solving RL problems in the Open AI gyms (agents playing various various video games). Note they do assume general knowledge of calculus, linear algebra and basic python coding.
Although the designer sets the reward policy–that is, the rules of the game–he gives the model no hints or suggestions for how to solve the game. It’s up to the model to figure out how to perform the task to maximize the reward, starting from totally random trials and finishing with sophisticated tactics and superhuman skills. By leveraging the power of search and many trials, reinforcement learning is currently the most effective way to hint machine’s creativity. In contrast to human beings, artificial intelligence can gather experience from thousands of parallel gameplays if a reinforcement learning algorithm is run on a sufficiently powerful computer infrastructure
Deciding an action by applying some tactics
Performing the action
Obtaining a reward
Discovering new areas with the help of past experiences and improving the approach
Iteratively sticking to the strategy and performing the action until the machine learns properly
Riste recommends the following next steps: