Reinforcement Learning

Map situation to action by numeric reward signal for policy model

Approach for Sequential decision making problems (sequential decision making is everywhere)

Reinforcement Learning is process of resolving MDP

Unlike supervised and unsupervised

iid, RL considers

Compounding Error. RL addresses compounding error at each time step by considering distribution shift. However, SL considers distribution shift not for each inference, even with time-series data, but instead accounts for it indirectly within the model.

In actual training, the data structure is the same, but rewards are derived from the environment rather than from the ground truth data in supervised learning. The practical difference between supervised learning and reinforcement learning lies in whether there is interaction with the environment, whether it's offline or online, through model-based approaches.

Indirect supervision: an agent defined within a certain environment recognizes the current state and maximizes rewards among selectable actions

Reinforcement Learning Notion

Policy Gradient Theorem

Reinforcement Learning Method

Reinforcement Learning Term

Reward Maximization

Reinforcement Learning Usages

TRL

RL tool

Policy Distillation