Back to Search
Start Over
Policy Optimization via Importance Sampling
- Source :
- 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montr\'eal, Canada
- Publication Year :
- 2018
-
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.
Details
- Database :
- arXiv
- Journal :
- 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montr\'eal, Canada
- Publication Type :
- Report
- Accession number :
- edsarx.1809.06098
- Document Type :
- Working Paper