Reinforcement Learning with Case-Based Heuristics for RoboCup Soccer Keepaway
Publication Type:
Conference PaperSource:
2012 Brazilian Robotics Symposium and Latin American Robotics Symposium, Fortaleza, Brasil, p.7-13 (2012)Keywords:
Transfer learning; Robot soccerUsing Transfer Learning to Speed-Up Reinforcement Learning: A Case-Based Approach
Improving Reinforcement Learning by using Case-Based Heuristics
Publication Type:
Conference PaperSource:
ICCBR'09: 8th International Conference on Case-Based Reasoning, Lecture Notes in Artificial Intelligence, Springer, Volume 5650, p.75-89 (2009)Abstract:
This work presents a new approach that allows the use of cases in
a case base as heuristics to speed up Reinforcement Learning algorithms, combining
Case Based Reasoning (CBR) and Reinforcement Learning (RL) techniques.
This approach, called Case Based Heuristically Accelerated Reinforcement
Learning (CB-HARL), builds upon an emerging technique, the Heuristic
Accelerated Reinforcement Learning (HARL), in which RL methods are accelerated
by making use of heuristic information. CB-HARL is a subset of RL that
makes use of a heuristic function derived from a case base, in a Case Based Reasoning
manner. An algorithm that incorporates CBR techniques into the Heuristically
Accelerated Q–Learning is also proposed. Empirical evaluations were conducted
in a simulator for the RoboCup Four-Legged Soccer Competition, and
results obtained shows that using CB-HARL, the agents learn faster than using
either RL or HARL methods.
Automatic Selection of Object Recognition Methods using Reinforcement Learning.
Case-Based Multiagent Reinforcement Learning: Cases as Heuristics for Selection of Actions
Should I Trust my Teammates? An experiment in Heuristic Multiagent Reinforcement Learning
Publication Type:
Conference PaperSource:
IJCAI Workshop on Grand Challenges for Reasoning from Experiences, IJCAI, Los Angeles, California, p.11-15 (2009)Keywords:
Reinforcement Learning; Multiagent Learning