Shangtong Zhang | DeepAI

AI Chat

Featured Co-authors

Hao Chen
339 publications
Bo Liu
167 publications
Oriol Vinyals
101 publications
Shimon Whiteson
97 publications
Nando de Freitas
83 publications
Thomas Lukasiewicz
82 publications
Richard S. Sutton
47 publications
Caglar Gulcehre
42 publications
Hado van Hasselt
40 publications
Adam White
37 publications
Aaron van den Oord
37 publications

∙ 08/07/2023

AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning

StarCraft II is one of the most challenging simulated reinforcement lear...

0 Michael Mathieu, et al. ∙

∙ 08/02/2023

Direct Gradient Temporal Difference Learning

Off-policy learning enables a reinforcement learning (RL) agent to reaso...

0 Xiaochi Qian, et al. ∙

∙ 01/31/2023

Improving Monte Carlo Evaluation with Offline Data

Monte Carlo (MC) methods are the most widely used methods to estimate th...

0 Shuze Liu, et al. ∙

∙ 02/14/2022

On the Chattering of SARSA with Linear Function Approximation

SARSA, a classical on-policy control algorithm for reinforcement learnin...

0 Shangtong Zhang, et al. ∙

∙ 11/04/2021

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

In this paper, we establish the global optimality and convergence rate o...

0 Shangtong Zhang, et al. ∙

∙ 08/11/2021

Truncated Emphatic Temporal Difference Methods for Prediction and Control

Emphatic Temporal Difference (TD) methods are a class of off-policy Rein...

0 Shangtong Zhang, et al. ∙

∙ 07/12/2021

Learning Expected Emphatic Traces for Deep RL

Off-policy sampling and experience replay are key for improving sample e...

0 Ray Jiang, et al. ∙

∙ 01/21/2021

Breaking the Deadly Triad with a Target Network

The deadly triad refers to the instability of a reinforcement learning a...

0 Shangtong Zhang, et al. ∙

∙ 01/08/2021

Average-Reward Off-Policy Policy Evaluation with Function Approximation

We consider off-policy policy evaluation with function approximation (FA...

0 Shangtong Zhang, et al. ∙

∙ 10/02/2020

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

We investigate the discounting mismatch in actor-critic algorithm implem...

1 Shangtong Zhang, et al. ∙

∙ 07/09/2020

Learning Retrospective Knowledge with Reverse Reinforcement Learning

We present a Reverse Reinforcement Learning (Reverse RL) approach for re...

25 Shangtong Zhang, et al. ∙

∙ 04/22/2020

Per-Step Reward: A New Perspective for Risk-Averse Reinforcement Learning

We present a new per-step reward perspective for risk-averse control in ...

15 Shangtong Zhang, et al. ∙

∙ 01/29/2020

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

We present GradientDICE for estimating the density ratio between the sta...

51 Shangtong Zhang, et al. ∙

∙ 11/11/2019

Provably Convergent Off-Policy Actor-Critic with Function Approximation

We present the first provably convergent off-policy actor-critic algorit...

26 Shangtong Zhang, et al. ∙

∙ 05/13/2019

Distributional Reinforcement Learning for Efficient Exploration

In distributional reinforcement learning (RL), the estimated distributio...

0 Borislav Mavrin, et al. ∙

∙ 05/12/2019

Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards

Intrinsic rewards are introduced to simulate how human intelligence work...

0 Yuhang Song, et al. ∙

∙ 05/03/2019

Deep Residual Reinforcement Learning

We revisit residual algorithms in both model-free and model-based reinfo...

38 Shangtong Zhang, et al. ∙

∙ 04/29/2019

DAC: The Double Actor-Critic Architecture for Learning Options

We reformulate the option framework as two parallel augmented MDPs. Unde...

16 Shangtong Zhang, et al. ∙

∙ 03/27/2019

Generalized Off-Policy Actor-Critic

We propose a new objective, the counterfactual objective, unifying exist...

28 Shangtong Zhang, et al. ∙

∙ 11/06/2018

ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search

In this paper, we propose an actor ensemble algorithm, named ACE, for co...

0 Shangtong Zhang, et al. ∙

∙ 11/05/2018

QUOTA: The Quantile Option Architecture for Reinforcement Learning

In this paper, we propose the Quantile Option Architecture (QUOTA) for e...

0 Shangtong Zhang, et al. ∙

∙ 12/04/2017

A Deeper Look at Experience Replay

Experience replay plays an important role in the success of deep reinfor...

0 Shangtong Zhang, et al. ∙

∙ 11/30/2017

Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control

Reinforcement learning and evolutionary strategy are two major approache...

0 Shangtong Zhang, et al. ∙

∙ 12/09/2016

Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks

Representations are fundamental to artificial intelligence. The performa...

0 Vivek Veeriah, et al. ∙

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