Alert button
Picture for Baohe Zhang

Baohe Zhang

Alert button

Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning

Jun 28, 2023
Shengchao Yan, Yuan Zhang, Baohe Zhang, Joschka Boedecker, Wolfram Burgard

Figure 1 for Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning
Figure 2 for Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning
Figure 3 for Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning
Figure 4 for Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning

Geometric regularity, which leverages data symmetry, has been successfully incorporated into deep learning architectures such as CNNs, RNNs, GNNs, and Transformers. While this concept has been widely applied in robotics to address the curse of dimensionality when learning from high-dimensional data, the inherent reflectional and rotational symmetry of robot structures has not been adequately explored. Drawing inspiration from cooperative multi-agent reinforcement learning, we introduce novel network structures for deep learning algorithms that explicitly capture this geometric regularity. Moreover, we investigate the relationship between the geometric prior and the concept of Parameter Sharing in multi-agent reinforcement learning. Through experiments conducted on various challenging continuous control tasks, we demonstrate the significant potential of the proposed geometric regularity in enhancing robot learning capabilities.

* accepted by RSS 2023 Workshop on Symmetries in Robot Learning 
Viaarxiv icon

Automated Reinforcement Learning (AutoRL): A Survey and Open Problems

Jan 11, 2022
Jack Parker-Holder, Raghu Rajan, Xingyou Song, André Biedenkapp, Yingjie Miao, Theresa Eimer, Baohe Zhang, Vu Nguyen, Roberto Calandra, Aleksandra Faust, Frank Hutter, Marius Lindauer

Figure 1 for Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Figure 2 for Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Figure 3 for Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Figure 4 for Automated Reinforcement Learning (AutoRL): A Survey and Open Problems

The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable agents. However, the success of RL agents is often highly sensitive to design choices in the training process, which may require tedious and error-prone manual tuning. This makes it challenging to use RL for new problems, while also limits its full potential. In many other areas of machine learning, AutoML has shown it is possible to automate such design choices and has also yielded promising initial results when applied to RL. However, Automated Reinforcement Learning (AutoRL) involves not only standard applications of AutoML but also includes additional challenges unique to RL, that naturally produce a different set of methods. As such, AutoRL has been emerging as an important area of research in RL, providing promise in a variety of applications from RNA design to playing games such as Go. Given the diversity of methods and environments considered in RL, much of the research has been conducted in distinct subfields, ranging from meta-learning to evolution. In this survey we seek to unify the field of AutoRL, we provide a common taxonomy, discuss each area in detail and pose open problems which would be of interest to researchers going forward.

Viaarxiv icon

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Feb 26, 2021
Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra

Figure 1 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Figure 2 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Figure 3 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Figure 4 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning algorithm, and as a result, they often possess tens of hyperparameters and architectural choices. For this reason, MBRL typically requires significant human expertise before it can be applied to new problems and domains. To alleviate this problem, we propose to use automatic hyperparameter optimization (HPO). We demonstrate that this problem can be tackled effectively with automated HPO, which we demonstrate to yield significantly improved performance compared to human experts. In addition, we show that tuning of several MBRL hyperparameters dynamically, i.e. during the training itself, further improves the performance compared to using static hyperparameters which are kept fixed for the whole training. Finally, our experiments provide valuable insights into the effects of several hyperparameters, such as plan horizon or learning rate and their influence on the stability of training and resulting rewards.

* 19 pages, accepted by AISTATS 2021 
Viaarxiv icon