Many algorithms such as Q-learning successfully address reinforcement learning in single-agent multi-time-step problems. In addition there are methods that address reinforcement l...
In many multi-agent applications such as distributed sensor nets, a network of agents act collaboratively under uncertainty and local interactions. Networked Distributed POMDP (ND...
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....
This paper presents a self-organizing cognitive architecture, known as TD-FALCON, that learns to function through its interaction with the environment. TD-FALCON learns the value ...