Mapping Elements of Reinforcement Learning to Human Emotions

Considerable overlap exists between emotion and Reinforcement Learning (RL). Emotion influences action selection while RL selects actions based on their anticipated result. Emotions also provide feedback on a situation, reflecting if the situation is desirable or not. The same type of feedback is given in RL based on the results of a state...

Learning while preventing mechanical failure due to random motions

In this thesis one of the negative effects of learning from scratch on the durability of LEO is analysed. LEO is one of the bipedal walking robots of the TU Delft Robotics Institute. It uses Reinforcement learning to learn a stable and energy efficient walking gait. LEO’s learning algorithm causes its gears to fail faster during the initial...

Reinforcement Learning on autonomous humanoid robots

Service robots have the potential to be of great value in households, health care and other labor intensive environments. However, these environments are typically unique, not very structured and frequently changing, which makes it difficult to make service robots robust and versatile through manual programming. Having robots learn to solve...

Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords

The reinforcement learning (RL) framework enables to construct controllers that try to find find an optimal control strategy in an unknown environment by trial-and-error. After selecting a control action, the controller receives a numerical reward. The reward signal is based on the current state of the environment and the applied control action....

Guaranteed globally optimal continuous reinforcement learning

Self-learning controllers offer various strong benefits over conventional controllers, the most important one being their ability to adapt to unexpected circumstances. Their application is however limited, the most important reason being that, for self-learning controllers to work on continuous domains, nonlinear function approximators are...

Avoiding failure states during reinforcement learning

The Delft Biorobotics Laboratory develops bipedal humanoid robots. One of these robots, called LEO, is designed to learn to walk using reinforcement learning. During learning, LEO will make mistakes and fall. These mistakes can cause serious dam- age to the system but are an integral part of the learning process. A likely solution is punishing...

Ant Colony Optimization for Control

The very basis of this thesis is the collective behavior of ants in colonies. Ants are an excellent example of how rather simple behavior on a local level can lead to complex behavior on a global level that is beneficial for the individuals. The key in the self-organization of ants is communication through pheromones. When an ant forages for...

A Comprehensive Survey of Multiagent Reinforcement Learning

Multiagent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, and economics. The complexity ofmany tasks arising in these domains makes them difficult to solve with preprogrammed agent behaviors. The agents must, instead, discover a solution on their own, using learning....

Experience-based model predictive control using reinforcement learning

Model predictive control (MPC) is becoming an increasingly popular method to select actions for controlling dynamic systems. TraditionallyMPC uses a model of the system to be controlled and a performance function to characterize the desired behavior of the system. The MPC agent finds actions over a finite horizon that lead the system into a...