Relational Reinforcement Learning
Machine Learning
Using Abstract Models of Behaviours to Automatically Generate Reinforcement Learning Hierarchies
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Integrating Experimentation and Guidance in Relational Reinforcement Learning
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
ML '92 Proceedings of the Ninth International Workshop on Machine Learning
RL-TOPS: An Architecture for Modularity and Re-Use in Reinforcement Learning
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Practical Reinforcement Learning in Continuous Spaces
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Learning measures of progress for planning domains
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Virtual clones: data-driven social navigation
IVA'11 Proceedings of the 10th international conference on Intelligent virtual agents
Multi-agent relational reinforcement learning
LAMAS'05 Proceedings of the First international conference on Learning and Adaption in Multi-Agent Systems
Hi-index | 0.00 |
Reinforcement learning deals with learning optimal or near optimal policies while interacting with the environment. Application domains with many continuous variables are difficult to solve with existing reinforcement learning methods due to the large search space. In this paper, we use a relational representation to define powerful abstractions that allow us to incorporate domain knowledge and re-use previously learned policies in other similar problems. We also describe how to learn useful actions from human traces using a behavioural cloning approach combined with an exploration phase. Since several conflicting actions may be induced for the same abstract state, reinforcement learning is used to learn an optimal policy over this reduced space. It is shown experimentally how a combination of behavioural cloning and reinforcement learning using a relational representation is powerful enough to learn how to fly an aircraft through different points in space and different turbulence conditions.