How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies
This incremental improvement addresses the instabilities and local optima in deep reinforcement learning for tasks approaching real-world complexity.
The paper tackles the problem of improving deep Q-network (DQN) learning efficiency by dynamically adjusting the discount factor and learning rate, showing that this approach significantly reduces the number of learning steps and outperforms original DQN in experiments.
Using deep neural nets as function approximator for reinforcement learning tasks have recently been shown to be very powerful for solving problems approaching real-world complexity. Using these results as a benchmark, we discuss the role that the discount factor may play in the quality of the learning process of a deep Q-network (DQN). When the discount factor progressively increases up to its final value, we empirically show that it is possible to significantly reduce the number of learning steps. When used in conjunction with a varying learning rate, we empirically show that it outperforms original DQN on several experiments. We relate this phenomenon with the instabilities of neural networks when they are used in an approximate Dynamic Programming setting. We also describe the possibility to fall within a local optimum during the learning process, thus connecting our discussion with the exploration/exploitation dilemma.