In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductive bias that encodes the natural ordering between discrete actions. This ordinal architecture further significantly improves the performance of PPO/TRPO.
@article{arxiv.1901.10500,
title = {Discretizing Continuous Action Space for On-Policy Optimization},
author = {Yunhao Tang and Shipra Agrawal},
journal= {arXiv preprint arXiv:1901.10500},
year = {2020}
}
Comments
Accepted at AAAI Conference on Artificial Intelligence (2020) in New York, NY, USA. An open source implementation can be found at https://github.com/robintyh1/onpolicybaselines