Definition
Reinforcement learning (RL) techniques are a set of solutions for optimal long-term action choice such that actions take into account both immediate and delayed consequences. They fall into two broad classes. Model-based approaches assume an explicit model of the environment and the agent. The model describes the consequences of actions and the associated returns. From this, optimal policies can be inferred. Psychologically, model-based descriptions apply to goal-directed decisions, in which choices reflect current preferences over outcomes. Model-free approaches forgo any explicit knowledge of the dynamics of the environment or the consequences of actions and evaluate how good actions are through trial-and-error learning. Model-free values underlie habitual and Pavlovian conditioned responses that are emitted reflexively when faced with certain stimuli. While model-based techniques have substantial computational demands, model-free techniques require extensive experience.
De...
This is a preview of subscription content, log in via an institution to check access.
References
Balleine B, Dickinson A (1994) Role of cholecystokinin in the motivational control of instrumental action in rats. Behav Neurosci 108(3):590–605
Barto A, Sutton R, Anderson C (1983) Neuronlike elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern 13(5):834–846
Bayer HM, Glimcher PW (2005) Midbrain dopamine neurons encode a quantitative reward prediction error signal. Neuron 47(1):129–141
Bayer HM, Lau B, Glimcher PW (2007) Statistics of midbrain dopamine neuron spike trains in the awake primate. JNeurophysiol 98(3):1428–1439
Bellman RE (1957) Dynamic programming. Princeton University Press, Princeton
Bertsekas DP, Tsitsiklis JN (1996) Neuro-dynamic programming. Athena Scientific, Belmon
Boutilier C, Dearden R, Goldszmidt M (1995) Exploiting structure in policy construction. In: Proceedings of the IJCAI Montreal, Quebec, Canada August 20–25,1995, vol 14, pp 1104–1113
Bouton ME (2006) Learning and behavior: a contemporary synthesis. Sinauer, Sunderland
Campbell M, Hoane A et al (2002) Deep blue. Artif Intell 134(1–2):57–83
Cardinal RN, Parkinson JA, Lachenal G, Halkerston KM, Rudarakanchana N, Hall J, Morrison CH, Howes SR, Robbins TW, Everitt BJ (2002) Effects of selective excitotoxic lesions of the nucleus accumbens core, anterior cingulate cortex, and central nucleus of the amygdala on autoshaping performance in rats. Behav Neurosci 116(4):553–567
Corbit LH, Balleine BW (2005a) Double dissociation of basolateral and central amygdala lesions on the general and outcome-specific forms of Pavlovian-instrumental transfer. J Neurosci 25(4):962–970
Balleine BW, Corbit LH (2005b) Double dissociation of nucleus accumbens core and shell on the general and ouctome-specific forms of Pavlovian-instrumental transfer. Program No. 71.16. 2005 Neuroscience Meeting Planner. Washington, DC: Society for Neuroscience, 2005. Online
D’Ardenne K, McClure SM, Nystrom LE, Cohen JD (2008) Bold responses reflecting dopaminergic signals in the human ventral tegmental area. Science 319(5867):1264–1267
Daw ND, Niv Y, Dayan P (2005) Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral control. Nat Neurosci 8(12):1704–1711
Daw ND, Gershman SJ, Seymour B, Dayan P, Dolan RJ (2011) Model-based influences on humans’ choices and striatal prediction errors. Neuron 69(6):1204–1215
Day JJ, Roitman MF, Wightman RM, Carelli RM (2007) Associative learning mediates dynamic shifts in dopamine signaling in the nucleus accumbens. Nat Neurosci 10(8):1020–1028
Dayan P, Berridge KC (2013) Pavlovian values. Cogn Affect Behav Neurosci. 2014 Mar 20. [Epub ahead of print] doi: 10.3758/s13415-014-0277-8
Dayan P, Niv Y, Seymour B, Daw ND (2006) The misbehavior of value and the discipline of the will. Neural Netw 19(8):1153–1160
Dickinson A, Dearing MF (1979) Appetitive-aversive interactions and inhibitory processes. In: Dickinson A, Boakes RA (eds) Mechanisms of learning and motivation. Erlbaum, Hillsdale, pp 203–231
Dickinson A, Smith J, Mirenowicz J (2000) Dissociation of Pavlovian and instrumental incentive learning under dopamine antagonists. Behav Neurosci 114(3):468–483
Dietterich TG (1999) Hierarchical reinforcement learning with the maxq value function decomposition. CoRR, cs.LG/9905014
Enomoto K, Matsumoto N, Nakai S, Satoh T, Sato TK, Ueda Y, Inokawa H, Haruno M, Kimura M (2011) Dopamine neurons learn to encode the long-term value of multiple future rewards. Proc Natl Acad Sci U S A 108(37):15462–15467
Flagel SB, Clark JJ, Robinson TE, Mayo L, Czuj A, Willuhn I, Akers CA, Clinton SM, Phillips PEM, Akil H (2011) A selective role for dopamine in stimulus-reward learning. Nature 469(7328):53–57
Frank MJ, Seeberger LC, O’Reilly RC (2004) By carrot or by stick: cognitive reinforcement learning in Parkinsonism. Science 306(5703):1940–1943
Gillan CM, Papmeyer M, Morein-Zamir S, Sahakian BJ, Fineberg NA, Robbins TW, de Wit S (2011) Disruption in the balance between goal-directed behavior and habit learning in obsessive-compulsive disorder. Am J Psychiatry 168(7):718–726
Gillan CM, Morein-Zamir S, Urcelay GP, Sule A, Voon V, Apergis-Schoute AM, Fineberg NA, Sahakian BJ, Robbins TW (2014) Enhanced avoidance habits in obsessive-compulsive disorder. Biol Psychiatry 75:631–638
Gläscher J, Daw N, Dayan P, O’Doherty JP (2010) States versus rewards: dissociable neural prediction error signals underlying model-based and model-free reinforcement learning. Neuron 66(4):585–595
Guitart-Masip M, Fuentemilla L, Bach DR, Huys QJM, Dayan P, Dolan RJ, Duzel E (2011) Action dominates valence in anticipatory representations in the human striatum and dopaminergic midbrain. J Neurosci 31(21):7867–7875
Hampton AN, Bossaerts P, O’Doherty JP (2006) The role of the ventromedial pre-frontal cortex in abstract state-based inference during decision making in humans. J Neurosci 26(32):8360–8367, 6
Hull C (1943) Principles of behavior. Appleton, New York
Huys QJM (2007) Reinforcers and control. Towards a computational etiology of depression. PhD thesis, Gatsby Computational Neuroscience Unit, UCL, University of London
Huys QJM, Tobler PT, Hasler G, Flagel S. The role of learning-related dopamine signals in addiction vulnerability. Prog Neurobiol (In Press)
Huys QJM, Cools R, Gölzer M, Friedel E, Heinz A, Dolan RJ, Dayan P (2011) Disentangling the roles of approach, activation and valence in instrumental and pavlovian responding. PLoS Comput Biol 7(4):e1002028
Huys QJM, Eshel N, O’Nions E, Sheridan L, Dayan P, Roiser JP (2012) Bonsai trees in your head: how the Pavlovian system sculpts goal-directed choices by pruning decision trees. PLoS Comput Biol 8(3):e1002410
Johnson A, Redish AD (2007) Neural ensembles in ca3 transiently encode paths forward of the animal at a decision point. J Neurosci 27(45):12176–12189
Kaelbling LP, Littman ML, Cassandra AR (1998) Planning and acting in partially observable stochastic domains. Artif intell 101(1):99–134
Kamin LJ (1969) Predictability, surprise, attention and conditioning. In: Campbell BA, Church RM (eds) Punishment and aversive behavior. Appleton, New York
Kearns M, Singh S (2002) Near-optimal reinforcement learning in polynomial time. Mach Learn 49(2–3):209–232
Keramati M, Dezfouli A, Piray P (2011) Speed/accuracy trade-off between the habitual and the goal-directed processes. PLoS Comput Biol 7(5):e1002055
Killcross S, Coutureau E (2003) Coordination of actions and habits in the medial prefrontal cortex of rats. Cereb Cortex 13(4):400–408
Knuth D, Moore R (1975) An analysis of alpha-beta pruning. Artif Intell 6(4):293–326
Kocsis L, Szepesvàri C (2006) Bandit based Monte-Carlo planning. In: Proceedings of the Machine learning: ECML 2006, Berlin, Germany, Springer, pp 282–293
Maia TV, Frank MJ (2011) From reinforcement learning models to psychiatric and neurological disorders. Nat Neurosci 14(2):154–162
McClure SM, Daw ND, Montague PR (2003) A computational substrate for incentive salience. Trends Neurosci 26:423–428
McDannald MA, Lucantonio F, Burke KA, Niv Y, Schoenbaum G (2011) Ventral striatum and orbitofrontal cortex are both required for model-based, but not model-free, reinforcement learning. J Neurosci 31(7):2700–2705
Montague PR, Dayan P, Sejnowski TJ (1996) A framework for mesencephalic dopamine systems based on predictive hebbian learning. J Neurosci 16(5):1936–1947
Morris G, Nevet A, Arkadir D, Vaadia E, Bergman H (2006) Midbrain dopamine neurons encode decisions for future action. Nat Neurosci 9(8):1057–1063
Nelson A, Killcross S (2006) Amphetamine exposure enhances habit formation. J Neurosci 26(14):3805–3812
Pfeiffer BE, Foster DJ (2013) Hippocampal place-cell sequences depict future paths to remembered goals. Nature 497(7447):74–79
Puterman ML (2005) Markov decision processes: discrete stochastic dynamic programming, Wiley series in probability and statistics. Wiley-Interscience, New York
Redish AD, Jensen S, Johnson A (2008) A unified framework for addiction: vulnerabilities in the decision process. Behav Brain Sci 31(4):415–437; discussion 437–487
Robbins TW, Gillan CM, Smith DG, de Wit S, Ersche KD (2012) Neurocognitive endophenotypes of impulsivity and compulsivity: towards dimensional psychiatry. Trends Cogn Sci 16(1):81–91
Robinson MJF, Berridge KC (2013) Instant transformation of learned repulsion into motivational “wanting”. Curr Biol 23(4):282–289
Roesch MR, Calu DJ, Schoenbaum G (2007) Dopamine neurons encode the better option in rats deciding between differently delayed or sized rewards. Nat Neurosci 10(12):1615–1624
Schoenbaum G, Roesch MR, Stalnaker TA, Takahashi YK (2009) A new perspective on the role of the orbitofrontal cortex in adaptive behaviour. Nat Rev Neurosci 10(12):885–892
Schultz W, Romo R (1990) Dopamine neurons of the monkey midbrain: contingencies of responses to stimuli eliciting immediate behavioral reactions. J Neurophysiol 63(3):607–624
Schultz W, Dayan P, Montague PR (1997) A neural substrate of prediction and reward. Science 275(5306):1593–1599
Sebold M, Deserno L, Nebe S, Schad D, Garbusow M, Hägele C, Keller J, Jünger E, Kathmann N, Smolka M, Rapp MA, Schlagenhauf F, Heinz A, Huys QJM. Model-based and model-free decisions in alcohol dependence. Neuropsychobiology (In Press)
Smith KS, Graybiel AM (2013) A dual operator view of habitual behavior reflecting cortical and striatal dynamics. Neuron 79(2):361–374
Steinberg EE, Keiflin R, Boivin JR, Witten IB, Deisseroth K, Janak PH (2013) A causal link between prediction errors, dopamine neurons and learning. Nat Neurosci 16(7):966–973
Sutton R (1990) Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceedings of the seventh international conference on machine learning, Austin, Texas, USA, vol 216, p 224
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction, Computation and machine learning. The MIT Press, Cambridge, MA
Sutton RS, Precup D, Singh S et al (1999) Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif Intell 112(1):181–211
Tobler PN, Fiorillo CD, Schultz W (2005) Adaptive coding of reward value by dopamine neurons. Science 307(5715):1642–1645
Tolman EC (1948) Cognitive maps in rats and men. Psychol Rev 55(4):189–208
Valentin VV, Dickinson A, O’Doherty JP (2007) Determining the neural substrates of goal-directed learning in the human brain. J Neurosci 27(15):4019–4026
Waelti P, Dickinson A, Schultz W (2001) Dopamine responses comply with basic assumptions of formal learning theory. Nature 412(6842):43–48
Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3):279–292
Wunderlich K, Smittenaar P, Dolan RJ (2012) Dopamine enhances model-based over model-free choice behavior. Neuron 75(3):418–424
Yin HH, Knowlton BJ, Balleine BW (2004) Lesions of dorsolateral striatum preserve outcome expectancy but disrupt habit formation in instrumental learning. Eur J Neurosci 19(1):181–189
Yin HH, Ostlund SB, Knowlton BJ, Balleine BW (2005) The role of the dorsomedial striatum in instrumental conditioning. Eur J Neurosci 22(2):513–523
Zaghloul KA, Blanco JA, Weidemann CT, McGill K, Jaggi JL, Baltuch GH, Kahana MJ (2009) Human substantia nigra neurons encode unexpected financial rewards. Science 323(5920):1496–1499
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Huys, Q.J.M., Cruickshank, A., Seriès, P. (2014). Reward-Based Learning, Model-Based and Model-Free. In: Jaeger, D., Jung, R. (eds) Encyclopedia of Computational Neuroscience. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-7320-6_674-1
Download citation
DOI: https://doi.org/10.1007/978-1-4614-7320-6_674-1
Received:
Accepted:
Published:
Publisher Name: Springer, New York, NY
Online ISBN: 978-1-4614-7320-6
eBook Packages: Springer Reference Biomedicine and Life SciencesReference Module Biomedical and Life Sciences
Publish with us
Chapter history
-
Latest
Reward-Based Learning, Model-Based and Model-Free- Published:
- 15 August 2019
DOI: https://doi.org/10.1007/978-1-4614-7320-6_674-2
-
Original
Reward-Based Learning, Model-Based and Model-Free- Published:
- 21 February 2014
DOI: https://doi.org/10.1007/978-1-4614-7320-6_674-1