Random Tag
Contributors
You are viewing revision 1.5.0, last edited by pedrochaves

Within the field of Machine learning, reinforcement learning refers to the study of methods of magnifying the reward given by interactions with the environment with no a priori knowledge of its properties. Strongly inspired by the work developed in behavioral psychology it is essentially a trial and error approach to find the best strategy.

Consider an agent that receives an input vector – I – from a complex environment of which it knows nothing of – S – informing it of its state. Based only on that information, the agent has to make a decision regarding which action to take, from a set, which will influence the state of the environment – A. This action will in itself change the state of the environment, which will result in a new input vector, and so on, each time also presenting the agent with the reward relative to its actions in the environment – r. The agent's goal is then to find the ideal strategy which will give the highest reward expectations over time, based on previous experience.

Exploration and Optimization

Knowing that randomly selecting the actions will result in poor performances, one of the biggest problems in reinforcement learning is exploring the avaliable set of responses to avoid getting stuck in sub-optimal choices and proceed to better ones. This is the problem of exploration, which is best described in the most studied reinforcement learning problem - the k-armed bandit....

(Read More)