Anthony Stein

Toward curious learning classifier systems

2017 · Proceedings of the Genetic and Evolutionary Computation Conference Companion

This paper proposes a novel approach to enhance the rather reactive knowledge generation process in Learning Classifier Systems (LCS) toward a more proactive means. We describe how concepts from the domain of Active Learning can …

Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

2021 · Algorithms

State-of-the-art Deep Reinforcement Learning Algorithms such as DQN and DDPG use the concept of a replay buffer called Experience Replay. The default usage contains only the experiences that have been gathered over the runtime. We …