Iterative Amortized Policy Optimization
This work addresses performance limitations in RL for continuous control, though it appears incremental as it builds on existing amortized optimization methods.
The paper tackled the problem of suboptimal policy estimates and restricted distributions in deep reinforcement learning for continuous control by introducing iterative amortized policy optimization, which improved performance over direct amortization on benchmark tasks.
Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the variational inference perspective on RL, policy networks, when used with entropy or KL regularization, are a form of \textit{amortized optimization}, optimizing network parameters rather than the policy distributions directly. However, \textit{direct} amortized mappings can yield suboptimal policy estimates and restricted distributions, limiting performance and exploration. Given this perspective, we consider the more flexible class of \textit{iterative} amortized optimizers. We demonstrate that the resulting technique, iterative amortized policy optimization, yields performance improvements over direct amortization on benchmark continuous control tasks.