A General Perspective on Objectives of Reinforcement Learning
This work provides a foundational perspective for researchers in reinforcement learning, though it appears incremental as it builds on existing definitions.
The paper tackles the problem of unifying reinforcement learning objectives by presenting three versions, culminating in a general objective that connects widely used techniques like TD(λ) and GAE, with potential application to extensive RL algorithms.
In this lecture, we present a general perspective on reinforcement learning (RL) objectives, where we show three versions of objectives. The first version is the standard definition of objective in RL literature. Then we extend the standard definition to the $λ$-return version, which unifies the standard definition of objective. Finally, we propose a general objective that unifies the previous two versions. The last version provides a high level to understand of RL's objective, where it shows a fundamental formulation that connects some widely used RL techniques (e.g., TD$(λ)$ and GAE), and this objective can be potentially applied to extensive RL algorithms.