Technical Note: \cal Q-Learning
Machine Learning
Robot shaping: developing autonomous agents through learning
Artificial Intelligence
Reinforcement Learning and Shaping: Encouraging Intended Behaviors
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Learning to Drive a Bicycle Using Reinforcement Learning and Shaping
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Autonomous shaping: knowledge transfer in reinforcement learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
Automatic shaping and decomposition of reward functions
Proceedings of the 24th international conference on Machine learning
Proceedings of the 25th international conference on Machine learning
Evolution of Valence Systems in an Unstable Environment
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Co-evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Potential-based shaping and Q-value initialization are equivalent
Journal of Artificial Intelligence Research
Transfer Learning for Reinforcement Learning Domains: A Survey
The Journal of Machine Learning Research
Multi-Task reinforcement learning: shaping and feature selection
EWRL'11 Proceedings of the 9th European conference on Recent Advances in Reinforcement Learning
Transfer in reinforcement learning via shared features
The Journal of Machine Learning Research
Learning potential functions and their representations for multi-task reinforcement learning
Autonomous Agents and Multi-Agent Systems
| Hi-index | 0.00 |
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, researchers have pre-specified a separate representation for shaping and value functions in multi-task settings. However, no work has made precise what distinguishes these representations, or what makes a good representation for either function. This paper shows two alternative methods by which an evolutionary algorithm can find a shaping function in multi-task RL without pre-specifying a separate representation. The second method, which uses an indirect fitness measure, is demonstrated to achieve similar performance to the first against a significantly lower computational cost. In addition, we define a formal categorisation of representations that makes precise what makes a good representation for shaping and value functions. We validate the categorisation with an evolutionary feature selection method and show that this method chooses the representations that our definitions predict are suitable.