Yunhao Tang

is this you? claim profile

∙ 1 follower
Columbia University

PhD student at Columbia IEOR

Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation

Model-agnostic meta-reinforcement learning requires estimating the Hessi...
06/24/2021 ∙ by Yunhao Tang, et al. ∙ 0 ∙ share

read it
Taylor Expansion of Discount Factors

In practical reinforcement learning (RL), the discount factor used for e...
06/11/2021 ∙ by Yunhao Tang, et al. ∙ 0 ∙ share

read it
Revisiting Peng's Q(λ) for Modern Reinforcement Learning

Off-policy multi-step reinforcement learning algorithms consist of conse...
02/27/2021 ∙ by Tadashi Kozuno, et al. ∙ 0 ∙ share

read it
Unlocking Pixels for Reinforcement Learning via Implicit Attention

There has recently been significant interest in training reinforcement l...
02/08/2021 ∙ by Krzysztof Choromanski, et al. ∙ 1 ∙ share

read it
ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning

We introduce ES-ENAS, a simple neural architecture search (NAS) algorith...
01/19/2021 ∙ by Xingyou Song, et al. ∙ 16 ∙ share

read it
Monte-Carlo Tree Search as Regularized Policy Optimization

The combination of Monte-Carlo tree search (MCTS) with deep reinforcemen...
07/24/2020 ∙ by Jean-Bastien Grill, et al. ∙ 5 ∙ share

read it
Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies

Off-policy learning algorithms have been known to be sensitive to the ch...
06/13/2020 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it
Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning

We propose a graphical model framework for goal-conditioned RL, with an ...
06/13/2020 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it
Self-Imitation Learning via Generalized Lower Bound Q-learning

Self-imitation learning motivated by lower-bound Q-learning is a novel a...
06/12/2020 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it
Taylor Expansion Policy Optimization

In this work, we investigate the application of Taylor expansions in rei...
03/13/2020 ∙ by Yunhao Tang, et al. ∙ 37 ∙ share

read it
Discrete Action On-Policy Learning with Action-Value Critic

Reinforcement learning (RL) in discrete action space is ubiquitous in re...
02/10/2020 ∙ by Yuguang Yue, et al. ∙ 14 ∙ share

read it
ES-MAML: Simple Hessian-Free Meta Learning

We introduce ES-MAML, a new framework for solving the model agnostic met...
09/25/2019 ∙ by Xingyou Song, et al. ∙ 16 ∙ share

read it
Reinforcement Learning with Chromatic Networks

We present a new algorithm for finding compact neural networks encoding ...
07/10/2019 ∙ by Xingyou Song, et al. ∙ 6 ∙ share

read it
Reinforcement Learning for Integer Programming: Learning to Cut

Integer programming (IP) is a general optimization framework widely appl...
06/11/2019 ∙ by Yunhao Tang, et al. ∙ 4 ∙ share

read it
Wasserstein Reinforcement Learning

We propose behavior-driven optimization via Wasserstein distances (WDs) ...
06/11/2019 ∙ by Aldo Pacchiano, et al. ∙ 1 ∙ share

read it
Variance Reduction for Evolution Strategies via Structured Control Variates

Evolution Strategies (ES) are a powerful class of blackbox optimization ...
05/29/2019 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it
Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes

We propose a new class of structured methods for Monte Carlo (MC) sampli...
05/29/2019 ∙ by Krzysztof Choromanski, et al. ∙ 8 ∙ share

read it
Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy

Due to the high variance of policy gradients, on-policy optimization alg...
03/13/2019 ∙ by Yunhao Tang, et al. ∙ 5 ∙ share

read it
Orthogonal Estimation of Wasserstein Distances

Wasserstein distances are increasingly used in a wide variety of applica...
03/09/2019 ∙ by Mark Rowland, et al. ∙ 7 ∙ share

read it
Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces

We present a new algorithm ASEBO for conducting optimization of high-dim...
03/07/2019 ∙ by Krzysztof Choromanski, et al. ∙ 12 ∙ share

read it
Discretizing Continuous Action Space for On-Policy Optimization

In this work, we show that discretizing action space for continuous cont...
01/29/2019 ∙ by Yunhao Tang, et al. ∙ 5 ∙ share

read it
Boosting Trust Region Policy Optimization by Normalizing Flows Policy

We propose to improve trust region policy search with normalizing flows ...
09/27/2018 ∙ by Yunhao Tang, et al. ∙ 5 ∙ share

read it
Implicit Policy for Reinforcement Learning

We introduce Implicit Policy, a general class of expressive policies tha...
06/10/2018 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it
Exploration by Distributional Reinforcement Learning

We propose a framework based on distributional reinforcement learning an...
05/04/2018 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it
Variational Deep Q Network

We propose a framework that directly tackles the probability distributio...
11/30/2017 ∙ by Yunhao Tang, et al. ∙ 1 ∙ share

read it

Yunhao Tang

Featured Co-authors

Mingyuan Zhou

Remi Munos

Michal Valko

Adrian Weller

Krzysztof Choromanski

Aldo Pacchiano

Vikas Sindhwani

Mark Rowland

Anna Choromanska

Will Dabney

Xingyou Song

Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation

Taylor Expansion of Discount Factors

Revisiting Peng's Q(λ) for Modern Reinforcement Learning

Unlocking Pixels for Reinforcement Learning via Implicit Attention

ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning

Monte-Carlo Tree Search as Regularized Policy Optimization

Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies

Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning

Self-Imitation Learning via Generalized Lower Bound Q-learning

Taylor Expansion Policy Optimization

Discrete Action On-Policy Learning with Action-Value Critic

ES-MAML: Simple Hessian-Free Meta Learning

Reinforcement Learning with Chromatic Networks

Reinforcement Learning for Integer Programming: Learning to Cut

Wasserstein Reinforcement Learning

Variance Reduction for Evolution Strategies via Structured Control Variates

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes

Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy

Orthogonal Estimation of Wasserstein Distances

Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces

Discretizing Continuous Action Space for On-Policy Optimization

Boosting Trust Region Policy Optimization by Normalizing Flows Policy

Implicit Policy for Reinforcement Learning

Exploration by Distributional Reinforcement Learning

Variational Deep Q Network