Answers are grounded in this paper and cite their sources.
An adaptive importance sampling technique improves the stability of value function estimators in off-policy reinforcement learning by actively controlling the bias-variance trade-off.
Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. The usefulness of the proposed approach is demonstrated through simulated swing-up inverted-pendulum problem.
No takes yet. Share an insight, caveat, or question.
Hachiya et al. (2009) studied Simulated swing-up inverted-pendulum problem. Adaptive importance sampling technique vs. Existing off-policy methods was evaluated on Trade-off between bias and variance in value function estimators.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: