Gamma-Nets: Generalizing Value Estimation over Timescale
Sherstan, Craig, Dohare, Shibhansh, MacGlashan, James, Günther, Johannes, Pilarski, Patrick M.
–arXiv.org Artificial Intelligence
We present $\Gamma$-nets, a method for generalizing value function estimation over timescale. By using the timescale as one of the estimator's inputs we can estimate value for arbitrary timescales. As a result, the prediction target for any timescale is available and we are free to train on multiple timescales at each timestep. Here we empirically evaluate $\Gamma$-nets in the policy evaluation setting. We first demonstrate the approach on a square wave and then on a robot arm using linear function approximation. Next, we consider the deep reinforcement learning setting using several Atari video games. Our results show that $\Gamma$-nets can be effective for predicting arbitrary timescales, with only a small cost in accuracy as compared to learning estimators for fixed timescales. $\Gamma$-nets provide a method for compactly making predictions at many timescales without requiring a priori knowledge of the task, making it a valuable contribution to ongoing work on model-based planning, representation learning, and lifelong learning algorithms.
arXiv.org Artificial Intelligence
Nov-23-2019
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- Europe
- Spain
- Galicia > Madrid (0.04)
- Catalonia > Barcelona Province
- Barcelona (0.04)
- France > Hauts-de-France
- Spain
- Asia > Taiwan
- Taiwan Province > Taipei (0.04)
- Oceania > Australia
- Genre:
- Research Report > New Finding (0.68)
- Industry:
- Education (0.48)
- Leisure & Entertainment > Games
- Computer Games (0.49)
- Technology: