94 citations · 215 across the 18 of their papers we have counts for
5 papers · 1 filter
Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping
Yujing Hu, Weixun Wang, Hangtian Jia +5
Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally ma…
Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising
Xiaotian Hao, Junqi Jin, Jianye Hao +7
Bipartite b-matching is fundamental in algorithm design, and has been widely applied into economic markets, labor markets, etc. These practical problems usually exhibit two distinc…
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…
KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge
Peng Zhang, Jianye Hao, Weixun Wang +4
Reinforcement learning agents usually learn from scratch, which requires a large number of interactions with the environment. This is quite different from the learning process of h…