Timezone: »

 
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation Q&A
Boyan Li · Hongyao Tang · YAN ZHENG · Jianye Hao · Pengyi Li · Zhaopeng Meng · LI Wang

Mon Dec 13 09:42 AM -- 09:45 AM (PST) @
in Deep Reinforcement Learning »
Event URL: https://openreview.net/forum?id=wQkaGq7Vz6q »

Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or continuous action space, while seldom take into account the hybrid action space. One naive way to address hybrid action RL is to convert the hybrid action space into a unified homogeneous action space by discretization or continualization, so that conventional RL algorithms can be applied. However, this ignores the underlying structure of hybrid action space and also induces the scalability issue and additional approximation difficulties, thus leading to degenerated results. In this paper, we propose Hybrid Action Representation (HyAR) to learn a compact and decodable latent representation space for the original hybrid action space. HyAR constructs the latent space and embeds the dependence between discrete action and continuous parameter via an embedding table and conditional Variantional Auto-Encoder (VAE). To further improve the effectiveness, the action representation is trained to be semantically smooth through unsupervised environmental dynamics prediction. Finally, the agent then learns its policy with conventional DRL algorithms in the learned representation space and interacts with the environment by decoding the hybrid action embeddings to the original action space. We evaluate HyAR in a variety of environments with discrete-continuous action space. The results demonstrate the superiority of HyAR when compared with previous baselines, especially for high-dimensional action spaces.

Author Information

Boyan Li (University of tianjin of china)
Hongyao Tang (Tianjin University)
YAN ZHENG (Tianjin University)
Jianye Hao (Tianjin University)
Pengyi Li (Tianjin University)
Zhaopeng Meng (School of Computer Software, Tianjin University)
LI Wang

More from the Same Authors