Deep Reinforcement Learning With Macro-Actions
This addresses the issue of sparse reward signals in deep RL for complex tasks like Atari games, but it is incremental as it builds on existing DQN methods.
The paper tackled the problem of slow convergence and unreliability in deep reinforcement learning by introducing macro-actions as a form of temporal abstraction, resulting in significant improvements in learning speed and even better scores than DQN on Atari 2600 games.
Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation modeling in the form of temporal abstraction to improve convergence and reliability of deep reinforcement learning approaches. We concentrate on macro-actions, and evaluate these on different Atari 2600 games, where we show that they yield significant improvements in learning speed. Additionally, we show that they can even achieve better scores than DQN. We offer analysis and explanation for both convergence and final results, revealing a problem deep RL approaches have with sparse reward signals.