177 citations · 263 across the 17 of their papers we have counts for
17 papers
T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler
Yuanqiang Yu, Tianpei Yang, Yongliang Lv +2
Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharin…
Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning
Zilin Zhao, Han Yang, Tianpei Yang +7
Complete your ad view and grab a 5-cent bonus! In incentivized advertising, a platform promises users a bonus before observing downstream ad revenue, encouraging them to click and…
NeurIPS 2022 Competition: Driving SMARTS
Amir Rasouli, Randy Goebel, Matthew E. Taylor +15
Driving SMARTS is a regular competition designed to tackle problems caused by the distribution shift in dynamic interaction contexts that are prevalent in real-world autonomous dri…
Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
Taher Jafferjee, Juliusz Ziomek, Tianpei Yang +6
Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it…
GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis
Yushi Cao, Zhiming Li, Tianpei Yang +5
Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and re…
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
Pengyi Li, Hongyao Tang, Tianpei Yang +8
Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is…
New physics in semileptonic transitions: rare hyperon vs. kaon decays
Li-Sheng Geng, Jorge Martin Camalich, Rui-Xiang Shi
We investigate the potential of rare hyperon decays to probe the short distance structure in the and transitions. Hyperon decays into neutrinos…
Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
Jianye Hao, Tianpei Yang, Hongyao Tang +5
Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant successes across a wide range of domains, including game AI, autonomo…
Learning to Shape Rewards using a Game of Two Partners
David Mguni, Taher Jafferjee, Jianhong Wang +9
Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engi…
Efficient Deep Reinforcement Learning via Adaptive Policy Transfer
Tianpei Yang, Jianye Hao, Zhaopeng Meng +8
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing tran…
An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning
Tianpei Yang, Weixun Wang, Hongyao Tang +9
Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can sh…
From Few to More: Large-scale Dynamic Multiagent Curriculum Learning
Weixun Wang, Tianpei Yang, Yong Liu +6
A lot of efforts have been devoted to investigating how agents can learn effectively and achieve coordination in multiagent systems. However, it is still challenging in large-scale…
Learning Action-Transferable Policy with Action Embedding
Yu Chen, Yingfeng Chen, Zhipeng Hu +4
Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different sta…
Action Semantics Network: Considering the Effects of Actions in Multiagent Systems
Weixun Wang, Tianpei Yang, Yong Liu +6
In multiagent systems (MASs), each agent makes individual decisions but all of them contribute globally to the system evolution. Learning in MASs is difficult since each agent's se…
Learning Shaping Strategies in Human-in-the-loop Interactive Reinforcement Learning
Chao Yu, Tianpei Yang, Wenxuan Zhu +2
Providing reinforcement learning agents with informationally rich human knowledge can dramatically improve various aspects of learning. Prior work has developed different kinds of…
Towards Efficient Detection and Optimal Response against Sophisticated Opponents
Tianpei Yang, Zhaopeng Meng, Jianye Hao +3
Multiagent algorithms often aim to accurately predict the behaviors of other agents and find a best response accordingly. Previous works usually assume an opponent uses a stationar…
Hierarchical Heuristic Learning towards Effcient Norm Emergence
Tianpei Yang, Jianye Hao, Zhaopeng Meng +2
Social norms serve as an important mechanism to regulate the behaviors of agents and to facilitate coordination among them in multiagent systems. One important research question is…