Combining Model-Free Q-Ensembles and Model-Based Approaches for Informed Exploration
Sankaranarayanan, Sreecharan, Annasamy, Raghuram Mandyam, Sycara, Katia, Rosé, Carolyn Penstein
–arXiv.org Artificial Intelligence
Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained. They have been shown to perform relatively well compared to other exploration strategies. Further, model-based approaches, such as encoder-decoder models have been used successfully for next frame prediction given previous frames. This paper proposes to integrate the model-free Q-ensembles and model-based approaches with the hope of compounding the benefits of both and achieving superior exploration as a result. Results show that a model-based trajectory memory approach when combined with Q-ensembles produces superior performance when compared to only using Q-ensembles.
arXiv.org Artificial Intelligence
Jun-12-2018
- Country:
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.15)
- Genre:
- Research Report > New Finding (0.34)
- Industry:
- Energy > Oil & Gas
- Upstream (0.36)
- Leisure & Entertainment > Games (0.47)
- Energy > Oil & Gas