Class information for:
Level 1: REINFORCEMENT LEARNING//ADAPTIVE DYNAMIC PROGRAMMING//APPROXIMATE DYNAMIC PROGRAMMING

Basic class information
ID Publications Average number
of references		 Avg. shr. active
ref. in WoS
6683 1382 29.9 36%


Bar chart of Publication_year

Last years might be incomplete

Classes in level above (level 2)


ID, lev.
above		 Publications Label for level above
1992 5055 ICCA JOURNAL//ICGA JOURNAL//REINFORCEMENT LEARNING

Terms with highest relevance score


Rank Term Type of term Relevance score
(tfidf)		 Class's shr.
of term's tot.
occurrences		 Shr. of publ.
in class containing
term		 Num. of
publ. in
class
1 REINFORCEMENT LEARNING Author keyword 74 14% 35% 488
2 ADAPTIVE DYNAMIC PROGRAMMING Author keyword 65 64% 5% 64
3 APPROXIMATE DYNAMIC PROGRAMMING Author keyword 42 36% 7% 93
4 ADAPTIVE DYNAMIC PROGRAMMING ADP Author keyword 31 76% 2% 22
5 ADAPTIVE CRITIC DESIGNS Author keyword 22 51% 2% 31
6 STATE MANAGEMENT CONTROL COMPLEX SYST Address 15 22% 4% 60
7 TEMPORAL DIFFERENCE METHODS Author keyword 13 80% 1% 8
8 Q LEARNING Author keyword 13 15% 6% 80
9 APPROXIMATE DYNAMIC PROGRAMMING ADP Author keyword 12 50% 1% 17
10 MULTIAGENT LEARNING Author keyword 10 38% 1% 20

Web of Science journal categories

Author Key Words


Rank Web of Science journal category Relevance score
(tfidf)		 Class's shr.
of term's tot.
occurrences		 Shr. of publ.
in class containing
term		 Num. of
publ. in
class		 LCSH search Wikipedia search
1 REINFORCEMENT LEARNING 74 14% 35% 488 Search REINFORCEMENT+LEARNING Search REINFORCEMENT+LEARNING
2 ADAPTIVE DYNAMIC PROGRAMMING 65 64% 5% 64 Search ADAPTIVE+DYNAMIC+PROGRAMMING Search ADAPTIVE+DYNAMIC+PROGRAMMING
3 APPROXIMATE DYNAMIC PROGRAMMING 42 36% 7% 93 Search APPROXIMATE+DYNAMIC+PROGRAMMING Search APPROXIMATE+DYNAMIC+PROGRAMMING
4 ADAPTIVE DYNAMIC PROGRAMMING ADP 31 76% 2% 22 Search ADAPTIVE+DYNAMIC+PROGRAMMING+ADP Search ADAPTIVE+DYNAMIC+PROGRAMMING+ADP
5 ADAPTIVE CRITIC DESIGNS 22 51% 2% 31 Search ADAPTIVE+CRITIC+DESIGNS Search ADAPTIVE+CRITIC+DESIGNS
6 TEMPORAL DIFFERENCE METHODS 13 80% 1% 8 Search TEMPORAL+DIFFERENCE+METHODS Search TEMPORAL+DIFFERENCE+METHODS
7 Q LEARNING 13 15% 6% 80 Search Q+LEARNING Search Q+LEARNING
8 APPROXIMATE DYNAMIC PROGRAMMING ADP 12 50% 1% 17 Search APPROXIMATE+DYNAMIC+PROGRAMMING+ADP Search APPROXIMATE+DYNAMIC+PROGRAMMING+ADP
9 MULTIAGENT LEARNING 10 38% 1% 20 Search MULTIAGENT+LEARNING Search MULTIAGENT+LEARNING
10 REINFORCEMENT LEARNING RL 9 28% 2% 26 Search REINFORCEMENT+LEARNING+RL Search REINFORCEMENT+LEARNING+RL

Key Words Plus


Rank Web of Science journal category Relevance score
(tfidf)		 Class's shr.
of term's tot.
occurrences		 Shr. of publ.
in class containing
term		 Num. of
publ. in
class
1 CRITIC DESIGNS 45 90% 1% 19
2 ADAPTIVE OPTIMAL CONTROL 31 92% 1% 12
3 ADAPTIVE CRITIC DESIGNS 28 55% 3% 35
4 OPTIMAL TRACKING CONTROL 23 76% 1% 16
5 TDLAMBDA 21 75% 1% 15
6 ZERO SUM GAMES 16 44% 2% 27
7 POLICY ITERATION 13 48% 1% 20
8 ONLINE LEARNING CONTROL 12 86% 0% 6
9 UNKNOWN DYNAMICS 8 62% 1% 8
10 TIME NONLINEAR SYSTEMS 7 27% 2% 23

Journals

Reviews


Title Publ. year Cit. Active
references		 % act. ref.
to same field
A comprehensive survey of multiagent reinforcement learning 2008 176 35 74%
Adaptive Dynamic Programming: An Introduction 2009 99 56 75%
Transfer Learning for Reinforcement Learning Domains: A Survey 2009 84 26 73%
Reinforcement learning: A survey 1996 1411 16 50%
Reinforcement learning and optimal adaptive control: An overview and implementation examples 2012 10 29 79%
Approximate dynamic programming strategies and their applicability for process control: A review and future directions 2004 29 38 63%
Reinforcement learning in robotics: A survey 2013 13 52 38%
Cooperative multi-agent learning: The state of the art 2005 198 35 17%
Evolutionary game theory and multi-agent reinforcement learning 2005 17 4 100%
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems 2012 6 21 71%

Address terms


Rank Address term Relevance score
(tfidf)		 Class's shr.
of term's tot.
occurrences		 Shr. of publ.
in class containing
term		 Num. of
publ. in
class
1 STATE MANAGEMENT CONTROL COMPLEX SYST 15 22% 4.3% 60
2 PL MECH ROBOT 4 67% 0.3% 4
3 TEAM SEQUEL 4 75% 0.2% 3
4 UTA 4 56% 0.4% 5
5 DISTRIBUTED SENSOR SYST GRP 2 67% 0.1% 2
6 MAIA PROJECT TEAM 2 67% 0.1% 2
7 ARLINGTON 2 50% 0.2% 3
8 CONTROL DYNAM SYST COMPUTAT CCDC 2 50% 0.2% 3
9 AI ROBOT 2 43% 0.2% 3
10 ARTIFICIAL INTELLIGENCE ROBOTS 1 50% 0.1% 2

Related classes at same level (level 1)


Rank Relatedness score Related classes
1 0.0000196321 POINT BASED VALUE ITERATION//PREDICTIVE STATE REPRESENTATIONS//POMDP
2 0.0000152478 IMITATION LEARNING//IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT//LEARNING FROM DEMONSTRATION
3 0.0000119848 AI ROBOT PROJECT//SIMULATION LEAGUE//ROBOT SOCCER
4 0.0000091409 LEARNING AUTOMATA//LEARNING AUTOMATA LA//MODELING OF ADAPTIVE SYSTEMS
5 0.0000091318 EVOLUTIONARY ROBOTICS//NAVAL WE ON//NEUROCONTROLLER ANALYSIS
6 0.0000087990 JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH//AUTOMATED PLANNING//DOMAIN INDEPENDENT PLANNING
7 0.0000087046 HOGG HUBERMAN MODEL//INNENWELT//LINUX DISTRIBUTIONS
8 0.0000085781 UP PEAK TRAFFIC//PROBABLE NUMBER OF STOPS//VERTICAL TRANSPORTATION
9 0.0000084750 LEARNING CLASSIFIER SYSTEMS//XCS//ILLIGAL
10 0.0000082035 STOCHASTIC APPROXIMATION//GRADIENT ESTIMATION//FREQUENCY DOMAIN METHODOLOGY