• Publications
  • Influence
VirtualHome: Simulating Household Activities Via Programs
TLDR
This paper crowd-source programs for a variety of activities that happen in people's homes, via a game-like interface used for teaching kids how to code, and implements the most common atomic actions in the Unity3D game engine, and uses them to "drive" an artificial agent to execute tasks in a simulated household environment.
Benchmarking Model-Based Reinforcement Learning
TLDR
This paper gathers a wide collection of MBRL algorithms and proposes over 18 benchmarking environments specially designed for MBRL, and describes three key research challenges for future MBRL research: the dynamics bottleneck, the planning horizon dilemma, and the early-termination dilemma.
NerveNet: Learning Structured Policy with Graph Neural Networks
TLDR
NerveNet is proposed to explicitly model the structure of an agent, which naturally takes the form of a graph, and is demonstrated to be significantly more transferable and generalizable than policies learned by other models and are able to transfer even in a zero-shot setting.
Exploring Model-based Planning with Policy Networks
TLDR
This paper proposes a novel MBRL algorithm, model-based policy planning (POPLIN), that combines policy networks with online planning and shows that POPLIN obtains state-of-the-art performance in the MuJoCo benchmarking environments, being about 3x more sample efficient than the state of theart algorithms, such as PETS, TD3 and SAC.
Learning to Generate Diverse Dance Motions with Transformer
TLDR
This work introduces a complete system for dance motion synthesis, which can generate complex and highly diverse dance sequences given an input music sequence, and presents a novel two-stream motion transformer generative model that can generate motion sequences with high flexibility.
Neural Graph Evolution: Towards Efficient Automatic Robot Design
TLDR
Neural Graph Evolution (NGE) is the first algorithm that can automatically discover kinematically preferred robotic graph structures, such as a fish with two symmetrical flat side-fins and a tail, or a cheetah with athletic front and back legs.
Physics-based Human Motion Estimation and Synthesis from Videos
TLDR
This work proposes a framework for training generative models of physically plausible human motion directly from monocular RGB videos, which are much more widely available and paves the way for large-scale, realistic and diverse motion synthesis.
Access points selection in super WiFi network powered by solar energy harvesting
TLDR
This paper study the access point selection strategy from users' perspectives and considers Super WiFi networks powered by solar energy harvesting, which has a remarkable performance improvement of utility over the myopic and random access strategies.
UniCon: Universal Neural Controller For Physics-based Character Motion
TLDR
A physics-based universal neural controller (UniCon) that learns to master thousands of motions with different styles by learning on large-scale motion datasets is proposed, demonstrating a significant improvement in efficiency, robustness and generalizability of UniCon over prior state-of-the-art systems.
Access Strategy in Super WiFi Network Powered by Solar Energy Harvesting: A POMDP Method
TLDR
This paper proposes a practical and efficient framework for multiple base stations access strategy in an EH powered Super Wi-Fi network, and considers the access strategy from the user's perspective, who exploits downlink transmission opportunities from one base station.