HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation

by   Boyan Li, et al.
Tianjin University

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.


Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space

Most existing deep reinforcement learning (DRL) frameworks consider eith...

Reinforcement learning for traffic signal control in hybrid action space

The prevailing reinforcement-learning-based traffic signal control metho...

Learn Continuously, Act Discretely: Hybrid Action-Space Reinforcement Learning For Optimal Execution

Optimal execution is a sequential decision-making problem for cost-savin...

Generative Slate Recommendation with Reinforcement Learning

Recent research has employed reinforcement learning (RL) algorithms to o...

Towards Governing Agent's Efficacy: Action-Conditional β-VAE for Deep Transparent Reinforcement Learning

We tackle the blackbox issue of deep neural networks in the settings of ...

LAW: Learning to Auto Weight

Example weighting algorithm is an effective solution to the training bia...

DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces

The ability to learn robust policies while generalizing over large discr...

Please sign up or login with your details

Forgot password? Click here to reset