We study a class of reinforcement learning problems where the reward signals for policy learning are generated by a discriminator that is dependent on and jointly optimized with the policy. This interdependence between the policy and the discriminator leads to an unstable learning process because reward signals from an immature discriminator are noisy and impede policy learning, and conversely, an untrained policy impedes discriminator learning. We call this learning setting $\textit{Internally Rewarded Reinforcement Learning}$ (IRRL) as the reward is not provided directly by the environment but $\textit{internally}$ by the discriminator. In this paper, we formally formulate IRRL and present a class of problems that belong to IRRL. We theoretically derive and empirically analyze the effect of the reward function in IRRL and based on these analyses propose the clipped linear reward function. Experimental results show that the proposed reward function can consistently stabilize the training process by reducing the impact of reward noise, which leads to faster convergence and higher performance compared with baselines in diverse tasks.

翻译：本文研究一类强化学习问题，其中策略学习的奖励信号由判别器生成，该判别器依赖于策略并与策略联合优化。策略与判别器之间的相互依赖会导致学习过程不稳定，因为不成熟判别器产生的奖励信号带有噪声，会阻碍策略学习；反之，未经训练的策略也会阻碍判别器学习。我们将这种学习机制称为“内部奖励强化学习”（IRRL），因为奖励并非直接由环境提供，而是由判别器“内部”生成。本文正式定义了IRRL，并提出了一类属于IRRL的问题。我们从理论上推导并实证分析了奖励函数在IRRL中的作用，并基于这些分析提出了裁剪线性奖励函数。实验结果表明，所提出的奖励函数通过降低奖励噪声的影响，能够持续稳定训练过程，从而在多种任务中相比基线方法实现更快的收敛速度和更高的性能。