Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments

Details Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments

2011-06-30

arxiv.org/abs/1107.0048v1

Journal Of Artificial Intelligence Research, Volume 23, pages 79-122, 2005

Computer Science

Artificial Intelligence

Scientific paper

10.1613/jair.1437

In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots. We argue that reinforcement learning can only be successfully applied to this case if strong assumptions are made on the characteristics of the environment in which the learning is performed, so that the relevant sensor readings and motor commands can be readily identified. The introduction of such assumptions leads to strongly-biased learning systems that can eventually lose the generality of traditional reinforcement-learning algorithms. In this line, we observe that, in realistic situations, the reward received by the robot depends only on a reduced subset of all the executed actions and that only a reduced subset of the sensor inputs (possibly different in each situation and for each action) are relevant to predict the reward. We formalize this property in the so called 'categorizability assumption' and we present an algorithm that takes advantage of the categorizability of the environment, allowing a decrease in the learning time with respect to existing reinforcement-learning algorithms. Results of the application of the algorithm to a couple of simulated realistic-robotic problems (landmark-based navigation and the six-legged robot gait generation) are reported to validate our approach and to compare it to existing flat and generalization-based reinforcement-learning approaches.

Affiliated with

Also associated with

No associations

Rating

Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-480022