Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning
This work addresses the challenge of improving learning efficiency in RL by utilizing prior solutions, which is incremental as it builds on existing entropy-regularized RL methods.
The paper tackles the problem of leveraging prior knowledge in reinforcement learning by developing a framework for reward shaping and task composition in entropy-regularized RL, showing that these methods lead to faster learning in experiments.
In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved tasks can allow agents to quickly solve new problems. In some cases, these new problems may be approximately solved by composing the solutions of previously solved primitive tasks (task composition). Otherwise, prior knowledge can be used to adjust the reward function for a new problem, in a way that leaves the optimal policy unchanged but enables quicker learning (reward shaping). In this work, we develop a general framework for reward shaping and task composition in entropy-regularized RL. To do so, we derive an exact relation connecting the optimal soft value functions for two entropy-regularized RL problems with different reward functions and dynamics. We show how the derived relation leads to a general result for reward shaping in entropy-regularized RL. We then generalize this approach to derive an exact relation connecting optimal value functions for the composition of multiple tasks in entropy-regularized RL. We validate these theoretical contributions with experiments showing that reward shaping and task composition lead to faster learning in various settings.