In some environments, a learning agent must learn to balance competing objectives. For example, a Q-learner agent may need to learn which choices expose the agent to risk and whic...
Imitation represents a powerful approach for programming and autonomous learning in robot and computer systems. An important aspect of imitation is the mapping of observations to ...
While the Belief, Desire, Intention (BDI) framework is one of the most influential and appealing approaches to rational agent architectures, a gulf often exists between the high-l...
We describe a robot control architecture which combines a stimulus-response subsystem for rapid reaction, with a search-based planner for handling unanticipated situations. The ro...
In this paper, we investigate the use of parallelization in reinforcement learning (RL), with the goal of learning optimal policies for single-agent RL problems more quickly by us...