Skip to main content
Springer Nature Link
Log in

Reinforcement Learning

  • Chapter
  • First Online:
A Guided Tour of Artificial Intelligence Research

Abstract

Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent faces a sequential decision-making problem where, at every time step, it observes its state, performs an action, receives a reward and moves to a new state. An RL agent learns by trial and error a good policy (or controller) based on observations and numeric reward feedback on the previously performed action. In this chapter, we present the basic framework of RL and recall the two main families of approaches that have been developed to learn a good policy. The first one, which is value-based, consists in estimating the value of an optimal policy, value from which a policy can be recovered, while the other, called policy search, directly works in a policy space. Actor-critic methods can be seen as a policy search technique where the policy value that is learned guides the policy improvement. Besides, we give an overview of some extensions of the standard RL framework, notably when risk-averse behavior needs to be taken into account or when rewards are not available or not known.

Olivier Buffet, Olivier Pietquin and Paul Weng—Equally contributed in this chapter.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    This section is mainly inspired by Deisenroth et al. (2011), although that survey focuses on a robotic framework.

  2. 2.

    Transformations can bring us in this setting.

References

  • Abbeel P, Coates A, Ng AY (2010) Autonomous helicopter aerobatics through apprenticeship learning. Int J Robot Res 29(13):1608–1639

    Article  Google Scholar 

  • Abbeel P, Ng A (2004) Apprenticeship learning via inverse reinforcement learning. In: International conference machine learning

    Google Scholar 

  • Akrour R, Schoenauer M, Sebag M (2013) ECML PKDD. Interactive robot education. Lecture notes in computer science

    Google Scholar 

  • Akrour R, Schoenauer M, Souplet J-C, Sebag M (2014) Programming by feedback. In: ICML

    Google Scholar 

  • Anderson BDO, Moore JB (2005) Optimal filtering. Dover Publications

    Google Scholar 

  • Antos A, Szepesvári C, Munos R (2008) Fitted Q-iteration in continuous action-space MDPs. In: Advances in neural information processing systems, pp 9–16

    Google Scholar 

  • Argall B, Chernova S, Veloso M, Browning B (2009) A survey of robot learning from demonstration. Robot Auton Syst 57(5):469–483

    Article  Google Scholar 

  • Artzner P, Delbaen F, Eber J, Heath D (1999) Coherent measures of risk. Math Financ 9(3):203–228

    Article  MathSciNet  Google Scholar 

  • Babes-Vroman M, Marivate V, Subramanian K, Littman M (2011) Apprenticeship learning about multiple intentions. In: ICML

    Google Scholar 

  • Bagnell JA, Schneider JG (2001) Autonomous helicopter control using reinforcement learning policysearch methods. In: Proceedings of the international conference on robotics and automation, pp 1615–1620

    Google Scholar 

  • Bagnell JA, Schneider JG (2003) Covariant policy search. In: Proceedings of the international joint conference on artifical intelligence

    Google Scholar 

  • Bai A, Wu F, Chen X (2013) Towards a principled solution to simulated robot soccer. In: RoboCup-2012: robot soccer world cup XVI. Lecture notes in artificial intelligence, vol 7500

    Google Scholar 

  • Baird L et al (1995) Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the twelfth international conference onmachine learning, pp 30–37

    Google Scholar 

  • Barbera S, Hammond P, Seidl C (1999) Handbook of utility theory. Springer, Berlin

    Google Scholar 

  • Bäuerle N, Rieder U (2011) Markov decision processes with applications to finance. Springer Science and Business Media

    Google Scholar 

  • Baxter J, Bartlett P (2001) Infinite-horizon policy-gradient estimation. J Artif Intell Res 15:319–350

    Google Scholar 

  • Baxter J, Bartlett P, Weaver L (2001) Experiments with infinite-horizon, policy-gradient estimation. J Artif Intell Res 15:351–381

    Google Scholar 

  • Bellman R, Dreyfus S (1959) Functional approximations and dynamic programming. Math Tables Aids Comput 13(68):247–251

    Google Scholar 

  • Bellman R, Kalaba R, Kotkin B (1963) Polynomial approximation-a new computational technique in dynamic programming: allocation processes. Math Comput 17(82):155–161

    Google Scholar 

  • Bogert K, Lin JF-S, Doshi P, Kulic D (2016) Expectation-maximization for inverse reinforcement learning with hidden data. In: AAMAS

    Google Scholar 

  • Bojarski M, Testa DD, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel LD, Monfort M, Muller U, Zhang J, Zhang X, Zhao J (2016) End to end learning for self-driving cars. Technical report, NVIDIA

    Google Scholar 

  • Borkar V, Jain R (2014) Risk-constrained Markov decision processes. IEEE Trans Autom Control 59(9):2574–2579

    Google Scholar 

  • Borkar VS (2010) Learning algorithms for risk-sensitive control. In: International symposium on mathematical theory of networks and systems

    Google Scholar 

  • Bou Ammar H, Tutunov R, Eaton E (2015) Safe policy search for lifelong reinforcement learning with sublinear regret. In: ICML

    Google Scholar 

  • Boularias A, Kober J, Peters J (2011) Relative entropy inverse reinforcement learning. In: AISTATS

    Google Scholar 

  • Boutilier C, Dearden R, Goldszmidt M (1995) Exploiting structure in policy construction. In: Proceedings of the fourteenth international joint conference on artificial intelligence, pp 1104–1111

    Google Scholar 

  • Boutilier C, Dearden R, Goldszmidt M (2000) Stochastic dynamic programming with factored representations. Artif Intell 121(1–2):49–107

    Google Scholar 

  • Bradtke SJ, Barto AG (1996) Linear least-squares algorithms for temporal difference learning. Machine Learning 22:33–57

    Google Scholar 

  • Burchfield B, Tomasi C, Parr R (2016) Distance minimization for reward learning from scored trajectories. In: AAAI

    Google Scholar 

  • Busa-Fekete R, Szörenyi B, Weng P, Cheng W, Hüllermeier E (2014) Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm. Mach Learn 97(3):327–351

    Google Scholar 

  • Busoniu L, Babuska R, De Schutter B (2010) Innovations in multi-agent systems and applications – 1, vol 310, chapter Multi-agent reinforcement learning: an overview, Springer, Berlin, pp 183–221

    Google Scholar 

  • Chernova S, Veloso M (2009) Interactive policy learning through confidence-based autonomy. J Artif Intell Res 34:1–25

    Google Scholar 

  • Choi D, Van Roy B (2006) A generalized Kalman filter for fixed point approximation and efficient temporal-difference learning. Discret Event Dyn Syst 16(2):207–239

    Google Scholar 

  • Choi J, Kim K-E (2011) Inverse reinforcement learning in partially observable environments. JMLR 12:691–730

    Google Scholar 

  • Choi J, Kim K-E (2012) Nonparametric Bayesian inverse reinforcement learning for multiple reward functions. In: NIPS

    Google Scholar 

  • Chow Y, Ghavamzadeh M (2014) Algorithms for CVaR optimization in MDPs. In: NIPS

    Google Scholar 

  • Chow Y, Ghavamzadeh M, Janson L, Pavone M (2016) Risk-constrained reinforcement learning with percentile risk criteria. JMLR 18(1)

    Google Scholar 

  • da Silva VF, Costa AHR, Lima P (2006) Inverse reinforcement learning with evaluation. In: IEEE ICRA

    Google Scholar 

  • Daniel C, Neumann G, Peters J (2012) Hierarchical relative entropy policy search. In: Proceedings of the international conference of artificial intelligence and statistics, pp 273–281

    Google Scholar 

  • de Boer P, Kroese D, Mannor S, Rubinstein R (2005) A tutorial on the cross-entropy method. Ann Oper Res 134(1):19–67

    Google Scholar 

  • de Farias D, Van Roy B (2003) The linear programming approach to approximate dynamic programming. Oper Res 51(6):850–865

    Google Scholar 

  • Degris T, Sigaud O, Wuillemin P-H (2006) Learning the structure of factored Markov decision processes in reinforcement learning problems. In: Proceedings of the 23rd international conference on machine learning

    Google Scholar 

  • Deisenroth MP, Neumann G, Peters J (2011) A survey on policy search for robotics. Found Trends Robot 2(1–2):1–142

    Google Scholar 

  • Deisenroth MP, Rasmussen CE (2011) PILCO: a model-based and data-efficient approach to policy search. In: Proceedings of the international conference on machine learning, pp 465–472

    Google Scholar 

  • Denuit M, Dhaene J, Goovaerts M, Kaas R, Laeven R (2006) Risk measurement with equivalent utility principles. Stat Decis 24:1–25

    Google Scholar 

  • Dimitrakakis C, Rothkopf CA (2011) Bayesian multitask inverse reinforcement learning. In: EWRL

    Google Scholar 

  • El Asri L, Laroche R, Pietquin O (2012) Reward function learning for dialogue management. In: STAIRS

    Google Scholar 

  • El Asri L, Piot B, Geist M, Laroche R, Pietquin O (2016) Score-based inverse reinforcement learning. In: AAMAS

    Google Scholar 

  • Engel Y, Mannor S, Meir R (2005) Reinforcement learning with Gaussian processes. In: Proceedings of the 22nd international conference on Machine learning, ACM, pp 201–208

    Google Scholar 

  • Ernst D, Geurts P, Wehenkel L (2005) Tree-based batch mode reinforcement learning. J Mach Learn Res 6(Apr):503–556

    Google Scholar 

  • Fürnkranz J, Hüllermeier E, Cheng W, Park S (2012) Preference-based reinforcement learning: a formal framework and a policy iteration algorithm. Mach Learn 89(1):123–156

    Google Scholar 

  • Geibel P, Wysotzky F (2005) Risk-sensitive reinforcement learning applied to control under constraints. JAIR 24:81–108

    Google Scholar 

  • Geist M, Pietquin O (2010a) Kalman temporal differences. J Artif Intell Res 39:483–532

    Google Scholar 

  • Geist M, Pietquin O (2010b) Statistically linearized least-squares temporal differences. In: 2010 international congress on ultra modern telecommunications and control systems and workshops (ICUMT), IEEE, pp 450–457

    Google Scholar 

  • Geist M, Pietquin O (2011) Parametric value function approximation: a unified view. In: ADPRL

    Google Scholar 

  • Geist M, Pietquin O (2013) Algorithmic survey of parametric value function approximation. IEEE Trans Neural Netw Learn Syst 24(6):845–867

    Google Scholar 

  • Ghavamzadeh M, Mannor S, Pineau J, Tamar A (2015) Bayesian reinforcement learning: a survey. Found Trends Mach Learn 8(5–6):359–492

    Google Scholar 

  • Gilbert H, Spanjaard O, Viappiani P, Weng P (2015) Solving MDPs with skew symmetric bilinear utility functions. In: International joint conference in artificial intelligence (IJCAI), pp 1989–1995

    Google Scholar 

  • Gilbert H, Weng P (2016) Quantile reinforcement learning. In: Asian workshop on reinforcement learning

    Google Scholar 

  • Gilbert H, Zanuttini B, Viappiani P, Weng P, Nicart E (2016) Model-free reinforcement learning with skew-symmetric bilinear utilities. In: International conference on uncertainty in artificial intelligence (UAI)

    Google Scholar 

  • Gordon GJ (1995) Stable function approximation in dynamic programming. In: Proceedings of the twelfth international conference onmachine learning, pp 261–268

    Google Scholar 

  • Gosavi AA (2014) Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques. Int J General Syst 43(6):649–669

    Google Scholar 

  • Grollman DH, Billard A (2011) Donut as I do: learning from failed demonstrations. In: IEEE ICRA

    Google Scholar 

  • Guestrin C, Hauskrecht M, Kveton B (2004) Solving factored MDPs with continuous and discrete variables. In: AAAI, pp 235–242

    Google Scholar 

  • Hansen N, Muller S, Koumoutsakos P (2003) Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evol Comput 11(1):1–18

    Google Scholar 

  • Heidrich-Meisner V, Igel C (2009) Neuroevolution strategies for episodic reinforcement learning. J Algorithms 64(4):152–168

    Google Scholar 

  • Hussein A, Gaber MM, Elyan E, Jayne C (2017) Imitation learning: a survey of learning methods. ACM Comput Surv

    Google Scholar 

  • Jiang DR, Powell WB (2017) Risk-averse approximate dynamic programming with quantile-based risk measures. Math Oper Res 43(2):347–692

    Google Scholar 

  • Julier SJ, Uhlmann JK (2004) Unscented filtering and nonlinear estimation. Proc IEEE 92(3):401–422

    Google Scholar 

  • Klein E, Geist M, Piot B, Pietquin O (2012) Inverse reinforcement learning through structured classification. In: NIPS

    Google Scholar 

  • Kober J, Oztop E, Peters J (2010) Reinforcement learning to adjust robot movements to new situations. In: Proceedings of the 2010 robotics: science and systems conference

    Google Scholar 

  • Kober J, Peters J (2010) Policy search for motor primitives in robotics. Mach Learn 1–33

    Google Scholar 

  • Kulkarni T, Narasimhan KR, Saeedi A, Tenenbaum J (2016) Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In: NIPS

    Google Scholar 

  • Lagoudakis MG, Parr R (2003) Least-squares policy iteration. J Mach Learn Res 4(Dec):1107–1149

    Google Scholar 

  • LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Google Scholar 

  • Lesner B, Zanuttini B (2011) Handling ambiguous effects in action learning. In: Proceedings of the 9th European workshop on reinforcement learning, p 12

    Google Scholar 

  • Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2016) Continuous control with deep reinforcement learning. In: ICLR

    Google Scholar 

  • Lin L-H (1992) Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach Learn 8(3/4):69–97

    Google Scholar 

  • Liu Y, Koenig S (2006) Functional value iteration for decision-theoretic planning with general utility functions. In: AAAI, AAAI, pp 1186–1193

    Google Scholar 

  • Lopes M, Melo F, Montesano L (2009) Active learning for reward estimation in inverse reinforcement learning. In: ECML/PKDD. vol 5782, Lecture notes in computer science, pp 31–46

    Google Scholar 

  • Machina M (1988) Expected utility hypothesis. In: Eatwell J, Milgate M, Newman P (eds) The new palgrave: a dictionary of economics. Macmillan, pp 232–239

    Google Scholar 

  • Matignon L, Laurent GJ, Le Fort-Piat N (2006) Reward function and initial values: better choices for accelerated goal-directed reinforcement learning. Lect Notes CS 1(4131):840–849

    Google Scholar 

  • Mihatsch O, Neuneier R (2002) Risk-sensitive reinforcement learning. Mach Learn 49:267–290

    Google Scholar 

  • Mnih V, Badia AP, Mirza M, Graves A, Lillicrap TP, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement. learning. In: ICML

    Google Scholar 

  • Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529–533

    Google Scholar 

  • Moldovan T, Abbeel P (2012) Risk aversion Markov decision processes via near-optimal Chernoff bounds. In: NIPS

    Google Scholar 

  • Neu G, Szepesvari C (2007) Apprenticeship learning using inverse reinforcement learning and gradient methods. In: UAI

    Google Scholar 

  • Neu G, Szepesvari C (2009) Training parsers by inverse reinforcement learning. Mach Learn 77:303–337

    Google Scholar 

  • Neumann G (2011) Variational inference for policy search in changing situations. In: Proceedings of the international conference on machine learning, pp 817–824

    Google Scholar 

  • Ng A, Russell S (2000) Algorithms for inverse reinforcement learning. In: ICML, Morgan Kaufmann

    Google Scholar 

  • Ng AY, Jordan M (2000) PEGASUS : A policy search method for large MDPs and POMDPs. In: Proceedings of the conference on uncertainty in artificial intelligence

    Google Scholar 

  • Nguyen QP, Low KH, Jaillet P (2015) Inverse reinforcement learning with locally consistent reward functions. In: NIPS

    Google Scholar 

  • Pasula HM, Zettlemoyer LS, Kaelbling LP (2007) Learning symbolic models of stochastic domains. J Artif Intell Res 29:309–352

    Google Scholar 

  • Peters J, Mülling K, Altun Y (2010) Relative entropy policy search. In: Proceedings of the national conference on artificial intelligence

    Google Scholar 

  • Peters J, Schaal S (2007) Applying the episodic natural actor-critic architecture to motorprimitive learning. In: Proceedings of the European symposium on artificial neural networks

    Google Scholar 

  • Peters J, Schaal S (2008a) Natural actor-critic. Neurocomputation 71(7–9):1180–1190

    Google Scholar 

  • Peters J, Schaal S (2008b) Reinforcement learning of motor skills with policy gradients. Neural Netw 4:682–697

    Google Scholar 

  • Piot B, Geist M, Pietquin O (2013) Learning from demonstrations: is it worth estimating a reward function? In: ECML PKDD, Lecture notes in computer science

    Google Scholar 

  • Piot B, Geist M, Pietquin O (2014) Boosted and Reward-regularized classification for apprenticeship learning. In: AAMAS, France, Paris, pp 1249–1256

    Google Scholar 

  • Pomerleau D (1989) Alvinn: an autonomous land vehicle in a neural network. In: NIPS

    Google Scholar 

  • Prashanth L, Ghavamzadeh M (2016) Variance-constrained actor-critic algorithms for discounted and average reward MDPs. Mach Learn

    Google Scholar 

  • Puterman M (1994) Markov decision processes: discrete stochastic dynamic programming. Wiley, New York

    Google Scholar 

  • Ramachandran D, Amir E (2007) Bayesian inverse reinforcement learning. In: IJCAI

    Google Scholar 

  • Randløv J, Alstrøm P (1998) 1998. Learning to drive a bicycle using reinforcement learning and shaping. In: ICML

    Google Scholar 

  • Ratliff N, Bagnell J, Zinkevich M (2006) Maximum margin planning. In: ICML

    Google Scholar 

  • Ratliff N, Bradley D, Bagnell JA, Chestnutt J (2007) Boosting structured prediction for imitation learning. In: NIPS

    Google Scholar 

  • Riedmiller M (2005) Neural fitted Q iteration-first experiences with a data efficient neural reinforcement learning method. In: ECML, vol 3720. Springer, Berlin, pp 317–328

    Google Scholar 

  • Roijers D, Vamplew P, Whiteson S, Dazeley R (2013) A survey of multi-objective sequential decision-making. J Artif Intell Res 48:67–113

    Google Scholar 

  • Russell S (1998) Learning agents for uncertain environments. In: Proceedings of the eleventh annual conference on Computational learning theory, ACM, pp 101–103

    Google Scholar 

  • Samuel A (1959) Some studies in machine learning using the game of checkers. IBM J Res Dev 3(3):210–229

    Google Scholar 

  • Schaul T, Quan J, Antonoglou I, Silver D (2016) Prioritized experience replay. In: ICLR

    Google Scholar 

  • Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: ICML

    Google Scholar 

  • Sebag M, Akrour R, Mayeur B, Schoenauer M (2016) Anti imitation-based policy learning. In: ECML PKDD, Lecture notes in computer science

    Google Scholar 

  • Sehnke F, Osendorfer C, Rückstieß T, Graves A, Peters J, Schmidhuber J (2010) Parameter-exploring policy gradients. Neural Netw 23(4):551–559

    Article  Google Scholar 

  • Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneerschelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484–489

    Google Scholar 

  • Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms. In: ICML

    Google Scholar 

  • Singh S, Kearns M, Litman D, Walker M (1999) Reinforcement learning for spoken dialogue systems. In: NIPS

    Google Scholar 

  • Spaan MT (2012) Reinforcement Learning, chapter Partially observable Markov decision processes. Springer, Berlin

    Google Scholar 

  • Sutton R, Maei H, Precup D, Bhatnagar S, Silver D, Szepesvári C, Wiewiora E (2009) Fast gradient-descent methods for temporal-difference learning with linear function approximation. In: ICML

    Google Scholar 

  • Syed U, Schapire RE (2008) A game-theoretic approach to apprenticeship learning. In: NIPS

    Google Scholar 

  • Szita I, Lörincz A (2006) Learning tetris using the noisy cross-entropy method. Neural Comput 18:2936–2941

    Article  Google Scholar 

  • Tamar A, Chow Y, Ghavamzadeh M, Mannor S (2015a) Policy gradient for coherent risk measures. In: NIPS

    Google Scholar 

  • Tamar A, Di Castro D, Mannor S (2012) Policy gradient with variance related risk criteria. In: ICML

    Google Scholar 

  • Tamar A, Di Castro D, Mannor S (2013) Temporal difference methods for the variance of the reward to go. In: ICML

    Google Scholar 

  • Tamar A, Glassner Y, Mannor S (2015b) Optimizing the CVaR via sampling. In: AAAI

    Google Scholar 

  • Taylor ME, Stone P (2009) Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res 10:1633–1685

    MathSciNet  MATH  Google Scholar 

  • Tesauro G (1995) Temporal difference learning and td-gammon. Commun ACM 38(3):58–68

    Article  Google Scholar 

  • Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: AAAI, pp 2094–2100

    Google Scholar 

  • van Otterlo M (2009) The logic of adaptive behavior. IOS

    Google Scholar 

  • Walsh T, Szita I, Diuk C, Littman M (2009) Exploring compact reinforcement-learning representations with linear regression. In: Proceedings of the 25th conference on uncertainty in artificial intelligence

    Google Scholar 

  • Wen M, Papusha I, Topcu U (2017) Learning from demonstrations with high-level side information. In: IJCAI

    Google Scholar 

  • Weng P, Busa-Fekete R, Hüllermeier E (2013) Interactive Q-learning with ordinal rewards and unreliable tutor. In: Workshop reinforcement learning with. generalized feedback, ECML/PKDD

    Google Scholar 

  • Werbos PJ (1990) Consistency of HDP applied to a simple reinforcement learning problem. Neural Netw 3:179–189

    Google Scholar 

  • Wierstra D, Schaul T, Glasmachers T, Sun Y, Peters J, Schmidhuber J (2014) Natural evolution strategies. JMLR 15:949–980

    MathSciNet  MATH  Google Scholar 

  • Williams R (1992) Simple statistical gradient-following algorithms for connectionnist reinforcement learning. Mach Learn 8(3):229–256

    MathSciNet  MATH  Google Scholar 

  • Wilson A, Fern A, Ray S, Tadepalli P (2007) Multi-task reinforcement learning: A hierarchical Bayesian approach. In: ICML

    Google Scholar 

  • Wilson A, Fern A, Tadepalli P (2012) A Bayesian approach for policy learning from trajectory preference queries. In: Advances in neural information processing systems

    Google Scholar 

  • Wirth C, Neumann G (2015) Model-free preference-based reinforcement learning. In: EWRL

    Google Scholar 

  • Wu Y, Tian Y (2017) Training agent for first-person shooter game with actor-critic curriculum learning. In: ICLR

    Google Scholar 

  • Wulfmeier M, Ondruska P, Posner I (2015) Maximum entropy deep inverse reinforcement learning. In: NIPS, Deep reinforcement learning workshop

    Google Scholar 

  • Xu X, Hu D, Lu X (2007) Kernel-based least squares policy iteration for reinforcement learning. IEEE Trans Neural Netw 18(4):973–992

    Article  Google Scholar 

  • Yu T, Zhang Z (2013) Optimal CPS control for interconnected power systems based on SARSA on-policy learning algorithm. In: Power system protection and control, pp 211–216

    Google Scholar 

  • Yue Y, Broder J, Kleinberg R, Joachims T (2012) The k-armed dueling bandits problem. J Comput Syst Sci 78(5):1538–1556

    Article  MathSciNet  Google Scholar 

  • Zhao Q, Chen S, Leung S, Lai K (2010) Integration of inventory and transportation decisions in a logistics system. Transp Res Part E: Logist Transp Rev 46(6):913–925

    Article  Google Scholar 

  • Ziebart B, Maas A, Bagnell J, Dey A (2010) Maximum entropy inverse reinforcement learning. In: AAAI

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. INRIA, Université de Lorraine, CNRS, UMR 7503 - LORIA, Nancy, France

    Olivier Buffet

  2. Université de Lille, CNRS, Centrale Lille, Inria, UMR 9189 - CRIStAL, Lille, France

    Olivier Pietquin

  3. Google Brain, Paris, France

    Olivier Pietquin

  4. Shanghai Jiao Tong University, University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai, China

    Paul Weng

Authors
  1. Olivier Buffet
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Olivier Pietquin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Paul Weng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Olivier Buffet .

Editor information

Editors and Affiliations

  1. CRIL-CNRS, Université d'Artois and Institut Universitaire de France, Lens, France

    Pierre Marquis

  2. Aix Marseille Université, Université de Toulon, CNRS, LIS, Marseille, France

    Odile Papini

  3. IRIT, CNRS and Université Paul Sabatier, Toulouse, France

    Henri Prade

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Buffet, O., Pietquin, O., Weng, P. (2020). Reinforcement Learning. In: Marquis, P., Papini, O., Prade, H. (eds) A Guided Tour of Artificial Intelligence Research. Springer, Cham. https://doi.org/10.1007/978-3-030-06164-7_12

Download citation

Publish with us

Policies and ethics

Search

Navigation