Boosting Soft Q-Learning by Bounding
This work addresses the challenge of leveraging past experience for more efficient task-solving in reinforcement learning, though it appears incremental as it builds on existing soft Q-learning methods.
The paper tackles the problem of improving training efficiency in soft Q-learning by deriving double-sided bounds on the optimal value function from any value function estimate, resulting in boosted performance as validated experimentally.
An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any value function estimate can also be used to derive double-sided bounds on the optimal value function. The derived bounds lead to new approaches for boosting training performance which we validate experimentally. Notably, we find that the proposed framework suggests an alternative method for updating the Q-function, leading to boosted performance.