Definition
Average-reward reinforcement learning (ARL) refers to learning policies that optimize the average reward per time step by continually taking actions and observing the outcomes including the next state and the immediate reward.
Motivation and Background
Reinforcement learning (RL) is the study of programs that improve their performance at some task by receiving rewards and punishments from the environment (Sutton and Barto 1998). RL has been quite successful in the automatic learning of good procedures for complex tasks such as playing Backgammon and scheduling elevators (Tesauro 1992; Crites and Barto 1998). In episodic domains in which there is a natural termination condition such as the end of the game in Backgammon, the obvious performance measure to optimize is the expected total reward per episode. But some domains such as elevator scheduling are...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Recommended Reading
Abounadi J, Bertsekas DP, Borkar V (2002) Stochastic approximation for non-expansive maps: application to Q-learning algorithms. SIAM J Control Optim 41(1):1–22
Barto AG, Bradtke SJ, Singh SP (1995) Learning to act using real-time dynamic programming. Artif Intell 72(1):81–138
Bertsekas DP (1995) Dynamic programming and optimal control. Athena Scientific, Belmont
Brafman RI, Tennenholtz M (2002) R-MAX – a general polynomial time algorithm for near-optimal reinforcement learning. J Mach Learn Res 2:213–231
Crites RH, Barto AG (1998) Elevator group control using multiple reinforcement agents. Mach Learn 33(2/3):235–262
Ghavamzadeh M, Mahadevan S (2006) Hierarchical average reward reinforcement learning. J Mach Learn Res 13(2):197–229
Kearns M, Singh S (2002) Near-optimal reinforcement learning in polynomial time. Mach Learn 49(2/3):209–232
Mahadevan S (1996) Average reward reinforcement learning: foundations, algorithms, and empirical results. Mach Learn 22(1/2/3):159–195
Marbach P, Mihatsch O, Tsitsiklis JN (2000) Call admission control and routing in integrated service networks using neuro-dynamic programming. IEEE J Sel Areas Commun 18(2): 197–208
Proper S, Tadepalli P (2006) Scaling model-based average-reward reinforcement learning for product delivery. In: European conference on machine learning, Berlin. Springer, pp 725–742
Puterman ML (1994) Markov decision processes: discrete dynamic stochastic programming. Wiley, New York
Schwartz A (1993) A reinforcement learning method for maximizing undiscounted rewards. In: Proceedings of the tenth international conference on machine learning, Amherst. Morgan Kaufmann, San Mateo, pp 298–305
Seri S, Tadepalli P (2002) Model-based hierarchical average-reward reinforcement learning. In: Proceedings of international machine learning conference, Sydney. Morgan Kaufmann, pp 562–569
Sutton R, Barto A (1998) Reinforcement learning: an introduction. MIT, Cambridge
Tadepalli P, Ok D (1998) Model-based average-reward reinforcement learning. Artif Intell 100:177–224
Tesauro G (1992) Practical issues in temporal difference learning. Mach Learn 8(3–4):257–277
Tsitsiklis J, Van Roy B (1999) Average cost temporal-difference learning. Automatica 35(11):1799–1808
Van Roy B, Tsitsiklis J (2002) On average versus discounted temporal-difference learning. Mach Learn 49(2/3):179–191
Wang G, Mahadevan S (1999) Hierarchical optimization of policy-coupled semi-Markov decision processes. In: Proceedings of the 16th international conference on machine learning, Bled, pp 464–473
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media New York
About this entry
Cite this entry
Tadepalli, P. (2017). Average-Reward Reinforcement Learning. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_17
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7687-1_17
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7685-7
Online ISBN: 978-1-4899-7687-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering