However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value functions.

In contrast, we design a discrete-time algorithm and derive its convergence rate solely under weakly monotone conditions.

We introduce a principled method for performing zero-shot transfer in reinforcement learning (RL) by exploiting approximate models of the environment. Zero-shot transfer in RL has been investigated by leveraging methods rooted in generalized policy improvement (GPI) and successor features (SFs).

While it is well suited to describe turn-based decision problems such as board games, this framework is ill suited for real-time applications in which the environment's state continues to evolve while the agent selects an action (Travnik et al., 2018). Nevertheless, this framework hasbeen used forreal-time problems using what areessentially tricks, e.g.

These Q values are often objectives that offline algorithms aim to approximate.