3412 search results - page 83 / 683 » Efficient Reinforcement Learning |
117
click to vote
ATAL
2008
Springer
15 years 2 months ago
2008
Springer
Many multiagent problems comprise subtasks which can be considered as reinforcement learning (RL) problems. In addition to classical temporal difference methods, evolutionary algo...
70
Voted
ICPR
2006
IEEE
16 years 1 months ago
2006
IEEE
To accelerate the learning of reinforcement learning, many types of function approximation are used to represent state value. However function approximation reduces the accuracy o...
ICRA
2005
IEEE
15 years 6 months ago
2005
IEEE
— This paper presents a new reinforcement learning algorithm for accelerating acquisition of new skills by real mobile robots, without requiring simulation. It speeds up Q-learni...
95
Voted
ATAL
2008
Springer
15 years 2 months ago
2008
Springer
Several multiagent reinforcement learning (MARL) algorithms have been proposed to optimize agents' decisions. Only a subset of these MARL algorithms both do not require agent...
107
Voted
TSMC
2008
15 years 16 days ago
2008
This paper describes several ensemble methods that combine multiple different reinforcement learning (RL) algorithms in a single agent. The aim is to enhance learning speed and fin...