• Publications
  • Influence
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
TLDR
Equipped with the global directional matching module and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation without using online fine-tuning. Expand
A theoretical and empirical analysis of Expected Sarsa
TLDR
It is proved that Expected Sarsa converges under the same conditions as SARSa and formulate specific hypotheses about when ExpectedSarsa will outperform SarsA and Q-learning, and it is demonstrated that Ex expected sarsa has significant advantages over these more commonly used methods. Expand
Reinforcement Learning in Continuous Action Spaces
TLDR
This work presents a new class of algorithms named continuous actor critic learning automaton (CACLA) that can handle continuous states and actions and shows that CACLA performs much better than the other algorithms, especially when it is combined with a Gaussian exploration method. Expand
Multi-Agent Reinforcement Leraning for Traffic Light Control
Reinforcement Learning and Markov Decision Processes
TLDR
This text introduces the intuitions and concepts behind Markov decision processes and two classes of algorithms for computing optimal behaviors: reinforcement learning and dynamic programming, and surveys efficient extensions of the foundational algorithms. Expand
Simulation and optimization of traffic in a city
Optimal traffic light control is a multi-agent decision problem, for which we propose to use reinforcement learning algorithms. Our algorithm learns the expected waiting times of cars for red andExpand
A Model Based Method for Automatic Facial Expression Recognition
TLDR
A system will be described that can classify expressions from one of the emotional categories joy, anger, sadness, surprise, fear and disgust with remarkable accuracy and is able to detect smaller, local facial features based on minimal muscular movements described by the Facial Action Coding System. Expand
HQ-Learning
TLDR
HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems to solve partially observable mazes with more states than those used in most previous POMDP work. Expand
Ensemble Algorithms in Reinforcement Learning
TLDR
Several ensemble methods that combine multiple different reinforcement learning (RL) algorithms in a single agent to enhance learning speed and final performance by combining the chosen actions or action probabilities of different RL algorithms are described. Expand
Solving POMDPs with Levin Search and EIRA
TLDR
An adaptive extension of LS ALS is introduced which uses experience to increase probabilities of instructions occurring in suc cessful programs found by LS to deal with cases where ALS does not lead to long term performance improvement, and EIRA works as a safety belt. Expand
...
1
2
3
4
5
...