Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Mengdi Wang

Mengdi Wang
Alert button

Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration


Jan 31, 2022
Chengzhuo Ni, Ruiqi Zhang, Xiang Ji, Xuezhou Zhang, Mengdi Wang

Add code
Alert button

Figure 1 for Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration
Figure 2 for Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration
Figure 3 for Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration
Figure 4 for Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Optimal policy evaluation using kernel-based temporal difference methods


Sep 24, 2021
Yaqi Duan, Mengdi Wang, Martin J. Wainwright

Add code
Alert button

Figure 1 for Optimal policy evaluation using kernel-based temporal difference methods
Figure 2 for Optimal policy evaluation using kernel-based temporal difference methods
Figure 3 for Optimal policy evaluation using kernel-based temporal difference methods
Figure 4 for Optimal policy evaluation using kernel-based temporal difference methods

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data


Jul 16, 2021
Jiandong Mu, Mengdi Wang, Feiwen Zhu, Jun Yang, Wei Lin, Wei Zhang

Add code
Alert button

Figure 1 for Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Figure 2 for Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Figure 3 for Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data
Figure 4 for Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control


Jun 15, 2021
Amrit Singh Bedi, Anjaly Parayil, Junyu Zhang, Mengdi Wang, Alec Koppel

Add code
Alert button

Figure 1 for On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control
Figure 2 for On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control
Figure 3 for On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control
Figure 4 for On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

1$\times$N Block Pattern for Network Sparsity


Jun 15, 2021
Mingbao Lin, Yuchao Li, Yuxin Zhang, Bohong Chen, Fei Chao, Mengdi Wang, Shen Li, Jun Yang, Rongrong Ji

Add code
Alert button

Figure 1 for 1$\times$N Block Pattern for Network Sparsity
Figure 2 for 1$\times$N Block Pattern for Network Sparsity
Figure 3 for 1$\times$N Block Pattern for Network Sparsity
Figure 4 for 1$\times$N Block Pattern for Network Sparsity

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient


Jun 04, 2021
Shaokun Zhang, Xiawu Zheng, Chenyi Yang, Yuchao Li, Yan Wang, Fei Chao, Mengdi Wang, Shen Li, Jun Yang, Rongrong Ji

Add code
Alert button

Figure 1 for You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Figure 2 for You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Figure 3 for You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Figure 4 for You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
* 12 pages, 3 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

MARL with General Utilities via Decentralized Shadow Reward Actor-Critic


May 29, 2021
Junyu Zhang, Amrit Singh Bedi, Mengdi Wang, Alec Koppel

Add code
Alert button

Figure 1 for MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
Figure 2 for MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
Figure 3 for MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
Figure 4 for MARL with General Utilities via Decentralized Shadow Reward Actor-Critic

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Compact CNNs via Collaborative Compression


May 24, 2021
Yuchao Li, Shaohui Lin, Jianzhuang Liu, Qixiang Ye, Mengdi Wang, Fei Chao, Fan Yang, Jincheng Ma, Qi Tian, Rongrong Ji

Add code
Alert button

Figure 1 for Towards Compact CNNs via Collaborative Compression
Figure 2 for Towards Compact CNNs via Collaborative Compression
Figure 3 for Towards Compact CNNs via Collaborative Compression
Figure 4 for Towards Compact CNNs via Collaborative Compression
* This paper is published in CVPR 2021 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Good State and Action Representations via Tensor Decomposition


May 03, 2021
Chengzhuo Ni, Anru Zhang, Yaqi Duan, Mengdi Wang

Add code
Alert button

Figure 1 for Learning Good State and Action Representations via Tensor Decomposition
Figure 2 for Learning Good State and Action Representations via Tensor Decomposition
Figure 3 for Learning Good State and Action Representations via Tensor Decomposition
Figure 4 for Learning Good State and Action Representations via Tensor Decomposition

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
<<
1
2
3
4
5
6
7
8
>>