no code implementations • 25 Aug 2023 • Shen Ren, Haosen Shi
Compact neural network offers many benefits for real-world applications.
no code implementations • ICCV 2023 • Haosen Shi, Shen Ren, Tianwei Zhang, Sinno Jialin Pan
A scheduling mechanism following the concept of curriculum learning is also designed to progressively change the sharing strategy to increase the level of sharing during the learning process.
no code implementations • 1 Jun 2021 • Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng
We find valued-based reinforcement learning methods with {\epsilon}-greedy mechanism are capable of enjoying three characteristics, Closed-form Diversity, Objective-invariant Exploration and Adaptive Trade-off, which help value-based methods avoid the policy collapse problem.
no code implementations • 9 May 2021 • Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, Haiyan Yin
We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI).