Deep Ordinal Reinforcement Learning
This work addresses the difficulty of designing numerical reward functions in reinforcement learning, offering an alternative that could simplify reward engineering, though it appears incremental as it adapts existing algorithms.
The paper tackles the challenge of using ordinal rewards instead of numerical rewards in reinforcement learning by presenting a general adaptation approach and introducing Ordinal Deep Q-Networks. The result shows that these ordinal variants achieve comparable performance to numerical methods on OpenAI Gym problems and may produce better results with simpler reward signals.
Reinforcement learning usually makes use of numerical rewards, which have nice properties but also come with drawbacks and difficulties. Using rewards on an ordinal scale (ordinal rewards) is an alternative to numerical rewards that has received more attention in recent years. In this paper, a general approach to adapting reinforcement learning problems to the use of ordinal rewards is presented and motivated. We show how to convert common reinforcement learning algorithms to an ordinal variation by the example of Q-learning and introduce Ordinal Deep Q-Networks, which adapt deep reinforcement learning to ordinal rewards. Additionally, we run evaluations on problems provided by the OpenAI Gym framework, showing that our ordinal variants exhibit a performance that is comparable to the numerical variations for a number of problems. We also give first evidence that our ordinal variant is able to produce better results for problems with less engineered and simpler-to-design reward signals.