RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning
Google DeepMindYouTube ↗
Further reading 4
Where does the learning signal come from? →Finding patterns in unlabeled data and choosing actions from rewards both dispense with a teacher giving the right answer. Only the latter must account for the consequences of a decision.Reward and fitness both give feedback. What changes? →In reinforcement learning, rewards inform action choices. MarI/O uses a fitness score to select entire networks across generations.Why can’t a policy classify each move in isolation? →An action changes the next situation and thus the choices and rewards still available. The dependence is temporal even when the delay is short.What cannot be recovered from the current observation? →Ask which distinctions the input representation discards. Earlier observations, feedback or prior knowledge may change what can be inferred.
Caption notes
Reinforcement learning concerns actions whose consequences affect later observations and rewards. The lecture distinguishes policy, value, model, planning and exploration.
Original passages · 6
the agent is actually influencing the data that it seesthe future is independent of the past given the presentin RL the environment is unknown in planning the environment is knownexploration means choosing to give up some reward that you know about in order to find out more about the environmentthere's no supervisor there's just this reward signalthe state is a sufficient statistic of the future