An Ensemble of Linearly Combined Reinforcement-Learning Agents

Reinforcement-learning (RL) algorithms are often tweaked and tuned to specific environments when applied, calling into question whether learning can truly be considered autonomous in these cases. In this work, we show how more robust learning across environments is possible by adopting an ensemble approach to reinforcement learning. Our approach learns a weighted linear combination of Q-values from multiple independent learning algorithms. In our evaluations in generalized RL environments, we find that the algorithm compares favorably to the best tuned algorithm. Our work provides a promising basis for further study into the use of ensemble methods in RL.