KIPPO: Koopman-Inspired Proximal Policy Optimization
This addresses the problem of high variance and instability in policy gradient methods for researchers and practitioners in reinforcement learning, offering an incremental improvement through an auxiliary network.
The paper tackled the challenge of unstable learning in reinforcement learning for environments with complex non-linear dynamics by introducing KIPPO, which learns an approximately linear latent-space representation using Koopman Operator Theory, resulting in 6-60% increased performance and up to 91% reduced variability over PPO on continuous control tasks.
Reinforcement Learning (RL) has made significant strides in various domains, and policy gradient methods like Proximal Policy Optimization (PPO) have gained popularity due to their balance in performance, training stability, and computational efficiency. These methods directly optimize policies through gradient-based updates. However, developing effective control policies for environments with complex and non-linear dynamics remains a challenge. High variance in gradient estimates and non-convex optimization landscapes often lead to unstable learning trajectories. Koopman Operator Theory has emerged as a powerful framework for studying non-linear systems through an infinite-dimensional linear operator that acts on a higher-dimensional space of measurement functions. In contrast with their non-linear counterparts, linear systems are simpler, more predictable, and easier to analyze. In this paper, we present Koopman-Inspired Proximal Policy Optimization (KIPPO), which learns an approximately linear latent-space representation of the underlying system's dynamics while retaining essential features for effective policy learning. This is achieved through a Koopman-approximation auxiliary network that can be added to the baseline policy optimization algorithms without altering the architecture of the core policy or value function. Extensive experimental results demonstrate consistent improvements over the PPO baseline with 6-60% increased performance while reducing variability by up to 91% when evaluated on various continuous control tasks.