Yangchen Pan | DeepAI

AI Chat

Featured Co-authors

Han Wang
86 publications
Martha White
65 publications
Sarath Chandar
58 publications
Pascal Poupart
56 publications
Jun Luo
55 publications
Adam White
37 publications
Hengshuai Yao
27 publications
Daniel Nikovski
26 publications
A. Rupam Mahmood
22 publications
Amir-massoud Farahmand
20 publications
Guojun Zhang
19 publications

∙ 08/13/2023

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

Stochastic gradient descent (SGD) and adaptive gradient methods, such as...

0 Avery Ma, et al. ∙

∙ 07/17/2023

An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient

Restricting the variance of a policy's return is a popular choice in ris...

0 Yudong Luo, et al. ∙

∙ 03/16/2023

Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning

Efficient exploration is critical in cooperative deep Multi-Agent Reinfo...

0 Xutong Zhao, et al. ∙

∙ 02/28/2023

The In-Sample Softmax for Offline Reinforcement Learning

Reinforcement learning (RL) agents can leverage batches of previously co...

0 Chenjun Xiao, et al. ∙

∙ 11/27/2022

Label Alignment Regularization for Distribution Shift

Recent work reported the label alignment property in a supervised learni...

0 Ehsan Imani, et al. ∙

∙ 05/22/2022

Memory-efficient Reinforcement Learning with Knowledge Consolidation

Artificial neural networks are promising as general function approximato...

0 Qingfeng Lan, et al. ∙

∙ 12/22/2021

An Alternate Policy Gradient Estimator for Softmax Policies

Policy gradient (PG) estimators for softmax policies are ineffective wit...

6 Shivam Garg, et al. ∙

∙ 07/19/2020

Beyond Prioritized Replay: Sampling States in Model-Based RL via Simulated Priorities

Model-based reinforcement learning (MBRL) can significantly improve samp...

12 Jincheng Mei, et al. ∙

∙ 02/16/2020

Maxmin Q-learning: Controlling the Estimation Bias of Q-learning

Q-learning suffers from overestimation bias, because it approximates the...

29 Qingfeng Lan, et al. ∙

∙ 02/14/2020

An implicit function learning approach for parametric modal regression

For multi-valued functions—such as when the conditional distribution on ...

13 Yangchen Pan, et al. ∙

∙ 02/14/2020

Frequency-based Search-control in Dyna

Model-based reinforcement learning has been empirically demonstrated as ...

0 Yangchen Pan, et al. ∙

∙ 11/19/2019

Deep Tile Coder: an Efficient Sparse Representation Learning Approach with applications in Reinforcement Learning

Representation learning is critical to the success of modern large-scale...

0 Yangchen Pan, et al. ∙

∙ 06/18/2019

Hill Climbing on Value Estimates for Search-control in Dyna

Dyna is an architecture for model-based reinforcement learning (RL), whe...

0 Yangchen Pan, et al. ∙

∙ 10/22/2018

Actor-Expert: A Framework for using Action-Value Methods in Continuous Action Spaces

Value-based approaches can be difficult to use in continuous action spac...

6 Sungsu Lim, et al. ∙

∙ 06/13/2018

Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control

Recent work has shown that reinforcement learning (RL) is a promising ap...

0 Yangchen Pan, et al. ∙

∙ 06/12/2018

Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains

Model-based strategies for control are critical to obtain sample efficie...

4 Yangchen Pan, et al. ∙

∙ 11/28/2016

Accelerated Gradient Temporal Difference Learning

The family of temporal difference (TD) methods span a spectrum from comp...

0 Yangchen Pan, et al. ∙

∙ 11/26/2015

Incremental Truncated LSTD

Balancing between computational efficiency and sample efficiency is an i...

0 Clement Gehring, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world