Making Deep Q-learning Methods Robust to Time Discretization

International Conference on Machine Learning (ICML)


Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sensitivity is key to making DRL applicable to real world problems. In this paper, we identify sensitivity to time discretization in near continuous-time environments as a critical factor; this covers, e.g., changing the number of frames per second, or the action frequency of the controller. Empirically, we find that Q-learning-based approaches such as Deep Q-learning (Mnih et al., 2015) and Deep Deterministic Policy Gradient (Lillicrap et al., 2015) collapse with small time steps. Formally, we prove that Q-learning does not exist in continuous time. We detail a principled way to build an off-policy RL algorithm that yields similar performances over a wide range of time discretizations, and confirm this robustness empirically.

Related Publications

All Publications

An Exploration of Embodied Visual Exploration

Santhosh K. Ramakrishnan, Dinesh Jayaraman, Kristen Grauman

arXiv - August 21, 2020

Audio-Visual Waypoints for Navigation

Changan Chen, Sagnik Majumder, Ziad Al-Halah, Ruohan Gao, Santhosh K. Ramakrishnan, Kristen Grauman

arXiv - August 21, 2020

Encoding Physical Constraints in Differentiable Newton-Euler Algorithm

Giovanni Sutanto, Austin S. Wang, Yixin Lin, Mustafa Mukadam, Gaurav S. Sukhatme, Akshara Rai, Franziska Meier

L4DC - June 10, 2020

Robust Market Equilibria with Uncertain Preferences

Riley Murray, Christian Kroer, Alex Peysakhovich, Parikshit Shah

AAAI - February 12, 2020

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy