Acceleration of game learning with prediction-based reinforcement learning -toward the emergence of planning behaviorOHIGASHI, Yu; OMORI, Takashi; MORIKAWA, Koji et al.Lecture notes in computer science. 2003, pp 786-793, issn 0302-9743, isbn 3-540-40408-2, 8 p.Conference Paper

Patching approximate solutions in reinforcement learningMIN SUB KIM; UTHER, William.Lecture notes in computer science. 2006, pp 258-269, issn 0302-9743, isbn 3-540-45375-X, 1Vol, 12 p.Conference Paper

Hippocampal replay contributes to within session learning in a temporal difference reinforcement learning modelJOHNSON, Adam; REDISH, A. David.Neural networks. 2005, Vol 18, Num 9, pp 1163-1171, issn 0893-6080, 9 p.Article

Feedforward neural networks in reinforcement learning applied to high-dimensional motor controlCOULOM, Rémi.Lecture notes in computer science. 2002, pp 403-413, issn 0302-9743, isbn 3-540-00170-0, 11 p.Conference Paper

Relational reinforcement learning for agents in worlds with objectsDZEROSKI, Saso.Adaptative agents and multi-agent systems (adaptation and multi-agent learning). Lecture notes in computer science. 2003, pp 306-322, issn 0302-9743, isbn 3-540-40068-0, 17 p.Book Chapter

A new way to introduce knowledge into reinforcement learningGARCIA, Pascal.Lecture notes in computer science. 2003, pp 157-168, issn 0302-9743, isbn 3-540-20121-1, 12 p.Conference Paper

Finding hidden hierarchy in reinforcement learningPOULTON, Geoff; YING GUO; WEN LU et al.Lecture notes in computer science. 2005, issn 0302-9743, isbn 3-540-28894-5, vol3, 554-561Conference Paper

Relational reinforcement learningDRIESSENS, Kurt.Lecture notes in computer science. 2001, pp 271-280, issn 0302-9743, isbn 3-540-42312-5Conference Paper

Learning to balance upright posture: What can be learnt using adaptive NN models?BORGHESE, N. Alberto.Lecture notes in computer science. 2002, pp 117-123, issn 0302-9743, isbn 3-540-44265-0, 7 p.Conference Paper

Karlsruhe brainstormers 2000 team descriptionRIEDMILLER, Martin; MERKE, Artur; MEIER, David et al.Lecture notes in computer science. 2001, pp 485-488, issn 0302-9743, isbn 3-540-42185-8Conference Paper

Towards a life-long learning soccer agentKLEINER, Alexander; DIETL, Markus; NEBEL, Bernhard et al.Lecture notes in computer science. 2003, pp 126-134, issn 0302-9743, isbn 3-540-40666-2, 9 p.Conference Paper

Combining exploitation-based and exploration-based approach in reinforcement learningIWATA, Kazunori; ITO, Nobuhiro; YAMAUCHI, Koichiro et al.Lecture notes in computer science. 2000, pp 326-331, issn 0302-9743, isbn 3-540-41450-9Conference Paper

Reinforcement learning : Past, present and futureSUTTON, R. S.Lecture notes in computer science. 1999, pp 195-197, issn 0302-9743, isbn 3-540-65907-2Conference Paper

Situating visual searchNAKAYAMA, Ken; MARTINI, Paolo.Vision research (Oxford). 2011, Vol 51, Num 13, pp 1526-1537, issn 0042-6989, 12 p.Article

Imitation and Reinforcement Learning: Practical Algorithms for Motor Primitives in RoboticsKOBER, Jens; PETERS, Jan.IEEE robotics & automation magazine. 2010, Vol 17, Num 2, pp 55-62, issn 1070-9932, 8 p.Article

Behavior construction and refinement from high-level specificationsMARTIGNONI, Andrew J; SMART, William D.SPIE proceedings series. 2004, pp 289-297, isbn 0-8194-5562-8, 9 p.Conference Paper

Forward and bidirectional planning based on reinforcement learning and neural networks in a simulated robotBALDASSARRE, Gianluca.Anticipatory behavior in adaptive learning systems : foundations, theories, and systems. Lecture notes in computer science. 2003, pp 179-200, issn 0302-9743, isbn 3-540-40429-5, 22 p.Book Chapter

A strategy for improved satisfaction of selling software agents in E-commerceTRAN, Thomas; COHEN, Robin.Lecture notes in computer science. 2003, pp 434-446, issn 0302-9743, isbn 3-540-40300-0, 13 p.Conference Paper

Abstraction, reformulation, and approximation (Kananaskis AB, 2-4 August 2002)Koenig, Sven; Holte, Robert C.Lecture notes in computer science. 2002, issn 0302-9743, isbn 3-540-43941-2, XI, 346 p, isbn 3-540-43941-2Conference Proceedings

A learning algorithm for buying and selling agents in electronic marketplacesTRAN, Thomas; COHEN, Robin.Lecture notes in computer science. 2002, pp 31-43, issn 0302-9743, isbn 3-540-43724-X, 13 p.Conference Paper

Speeding-up reinforcement learning with multi-step actionsSCHOKNECHT, Ralf; RIEDMILLER, Martin.Lecture notes in computer science. 2002, pp 813-818, issn 0302-9743, isbn 3-540-44074-7, 6 p.Conference Paper

Learning rates for Q-learningEVEN-DAR, Eyal; MANSOUR, Yishay.Lecture notes in computer science. 2001, pp 589-604, issn 0302-9743, isbn 3-540-42343-5Conference Paper

Using document structures for personal ontologies and user modelingKIM, Sanghee; HALL, Wendy; KEANE, Andy et al.Lecture notes in computer science. 2001, pp 240-242, issn 0302-9743, isbn 3-540-42325-7Conference Paper

Continual robot learning with constructive neural networksGROSSMANN, A; POLI, R.Lecture notes in computer science. 1998, pp 95-108, issn 0302-9743, isbn 3-540-65480-1Conference Paper

Q-learning of complex behaviours on a six-legged walking machineKIRCHNER, F.Robotics and autonomous systems. 1998, Vol 25, Num 3-4, pp 253-262, issn 0921-8890Article