Skip to yearly menu bar Skip to main content


Poster

Policy Optimization via Importance Sampling

Alberto Maria Metelli · Matteo Papini · Francesco Faccio · Marcello Restelli

Room 517 AB #109

Keywords: [ Reinforcement Learning and Planning ] [ Reinforcement Learning ] [ Markov Decision Processes ]


Abstract:

Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-trivial, as it requires to account for the variance of the objective function estimate. In this paper, we propose a novel, model-free, policy search algorithm, POIS, applicable in both action-based and parameter-based settings. We first derive a high-confidence bound for importance sampling estimation; then we define a surrogate objective function, which is optimized offline whenever a new batch of trajectories is collected. Finally, the algorithm is tested on a selection of continuous control tasks, with both linear and deep policies, and compared with state-of-the-art policy optimization methods.

Live content is unavailable. Log in and register to view live content