Reinforcement Learning Task

A Reinforcement Learning Task is an active learning task/serial decision task with a cost function and constraint rules.

• AKA: Reinforcement Learning.
• Context:
  • It can be solved by a Reinforcement Learning System that implements a Reinforcement Learning Algorithm.
• Example(s):
  • It can be an RL Benchmark Task, such as http://www.rl-competition.org/
  • a k-Armed Bandit Task.
  • Counter-Example(s):
  • an Unsupervised Learning Task.
  • a i.i.d. Learning Task.
• See: Active Learning, Exploration/Exploitation Tradeoff, Associative Reinforcement Learning; Autonomous Helicopter Flight Using Reinforcement Learning; Average-Reward Reinforcement Learning; Bayesian Reinforcement Learning; Dynamic Programming; Efficient Exploration in Reinforcement Learning; Gaussian Process Reinforcement Learning; Hierarchical Reinforcement Learning; Instance-Based Reinforcement Learning; Inverse Reinforcement Learning; Least Squares Reinforcement Learning Methods; Model-Based Reinforcement Learning; Policy Gradient Methods; Q-Learning; Relational Reinforcement Learning; Reward Shaping; Symbolic Dynamic Programming; Temporal Difference Learning; Value Function Approximation, Behaviorism, Software Agent, Game Theory, Control Theory, Operations Research, Information Theory, Simulation-Based Optimization, Genetic Algorithm, Optimal Control Theory, Bounded Rationality.

References

2013

• (Wikipedia, 2013) ⇒ http://en.wikipedia.org/wiki/reinforcement_learning Retrieved:2013-12-4.
  • Reinforcement learning is an area of machine learning inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. The problem, due to its generality, is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, statistics, and genetic algorithms. In the operations research and control literature, the field where reinforcement learning methods are studied is called approximate dynamic programming. The problem has been studied in the theory of optimal control, though most studies there are concerned with existence of optimal solutions and their characterization, and not with the learning or approximation aspects.

    In economics and game theory, reinforcement learning may be used to explain how equilibrium may arise under bounded rationality.

    In machine learning, the environment is typically formulated as a Markov decision process (MDP), and many reinforcement learning algorithms for this context are highly related to dynamic programming techniques. The main difference between the classical techniques and reinforcement learning algorithms is that the latter do not need knowledge about the MDP and they target large MDPs where exact methods become infeasible.

    Reinforcement learning differs from standard supervised learning in that correct input/output pairs are never presented, nor sub-optimal actions explicitly corrected. Further, there is a focus on on-line performance, which involves finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge). The exploration vs. exploitation trade-off in reinforcement learning has been most thoroughly studied through the multi-armed bandit problem and in finite MDPs.

2011

• (Peter Stone, 2011b) ⇒ Peter Stone. (2011). "Reinforcement Learning." In: (Sammut & Webb, 2011) p.849

---