Partial advantage estimator for proximal policy optimization
This work addresses bias reduction in advantage estimation for reinforcement learning practitioners, but it is incremental as it builds on existing GAE methods.
The paper tackled the problem of large bias in truncated Generalized Advantage Estimation (GAE) for policy gradient methods by proposing a partial GAE approach that uses only part of the truncated estimator, which significantly reduces bias from incomplete trajectories and yields better empirical results in MuJoCo and μRTS environments.
Estimation of value in policy gradient methods is a fundamental problem. Generalized Advantage Estimation (GAE) is an exponentially-weighted estimator of an advantage function similar to $λ$-return. It substantially reduces the variance of policy gradient estimates at the expense of bias. In practical applications, a truncated GAE is used due to the incompleteness of the trajectory, which results in a large bias during estimation. To address this challenge, instead of using the entire truncated GAE, we propose to take a part of it when calculating updates, which significantly reduces the bias resulting from the incomplete trajectory. We perform experiments in MuJoCo and $μ$RTS to investigate the effect of different partial coefficient and sampling lengths. We show that our partial GAE approach yields better empirical results in both environments.