Key points are not available for this paper at this time.
While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from high degrees of plasticity loss; and requires exploration to prevent premature convergence to local optima and maximize return. In this paper, we consider whether learned optimization can help overcome these problems. Our method, Learned Optimization for Plasticity, Exploration and Non-stationarity (OPEN), meta-learns an update rule whose input features and output structure are informed by previously proposed solutions to these difficulties. We show that our parameterization is flexible enough to enable meta-learning in diverse learning contexts, including the ability to use stochasticity for exploration. Our experiments demonstrate that when meta-trained on single and small sets of environments, OPEN outperforms or equals traditionally used optimizers. Furthermore, OPEN shows strong generalization across a distribution of environments and a range of agent architectures.
Building similarity graph...
Analyzing shared references across papers
Loading...
Goldie et al. (Tue,) studied this question.
www.synapsesocial.com/papers/68e60f66b6db6435875a2645 — DOI: https://doi.org/10.48550/arxiv.2407.07082
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:
Alexander David Goldie
Chris Xiaoxuan Lu
Matthew Thomas Jackson
Building similarity graph...
Analyzing shared references across papers
Loading...