151 citations · 606 across the 63 of their papers we have counts for
28 papers · 1 filter
Learning World Models with Identifiable Factorization
Yu-Ren Liu, Biwei Huang, Zhengmao Zhu +4
Extracting a stable and compact representation of the environment is crucial for efficient reinforcement learning in high-dimensional, noisy, and non-stationary environments. Diffe…
Beware of Instantaneous Dependence in Reinforcement Learning
Zhengmao Zhu, Yuren Liu, Honglong Tian +2
Playing an important role in Model-Based Reinforcement Learning (MBRL), environment models aim to predict future states based on the past. Existing works usually ignore instantaneo…
Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning
Yang Yu, Danruo Deng, Furui Liu +4
Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) consi…
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
Danruo Deng, Guangyong Chen, Yang Yu +2
Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. Recently proposed evidential neural networks explicitly account for different un…
Learning Physically Realizable Skills for Online Packing of General 3D Shapes
Hang Zhao, Zherong Pan, Yang Yu +1
We study the problem of learning online packing skills for irregular 3D shapes, which is arguably the most challenging setting of bin packing problems. The goal is to consecutively…
Model-based Reinforcement Learning with Multi-step Plan Value Estimation
Haoxin Lin, Yihao Sun, Jiaji Zhang +1
A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to sa…
Unified Policy Optimization for Continuous-action Reinforcement Learning in Non-stationary Tasks and Games
Rong-Jun Qin, Fan-Ming Luo, Hong Qian +1
This paper addresses policy learning in non-stationary environments and games with continuous actions. Rather than the classical reward maximization mechanism, inspired by the idea…
Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
Tian Xu, Ziniu Li, Yang Yu +1
Imitation learning learns a policy from expert trajectories. While the expert data is believed to be crucial for imitation quality, it was found that a kind of imitation learning a…
A Survey on Model-based Reinforcement Learning
Fan-Ming Luo, Tian Xu, Hang Lai +3
Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in play…
Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning
Xue-Kun Jin, Xu-Hui Liu, Shengyi Jiang +1
Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting. In this paper, we propose Hybrid Value Es…
Adversarial Counterfactual Environment Model Learning
Xiong-Hui Chen, Yang Yu, Zheng-Mao Zhu +8
A good model for action-effect prediction, named environment model, is important to achieve sample-efficient decision-making policy learning in many domains like robot control, rec…
Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble
Fan-Ming Luo, Xingchen Cao, Rong-Jun Qin +1
Recovering reward function from expert demonstrations is a fundamental problem in reinforcement learning. The recovered reward function captures the motivation of the expert. Agent…
Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library
Yangyang Hu, Yang Yu
Mathematical reasoning recently has been shown as a hard challenge for neural systems. Abilities including expression translation, logical reasoning, and mathematics knowledge acqu…
A Note on Target Q-learning For Solving Finite MDPs with A Generative Oracle
Ziniu Li, Tian Xu, Yang Yu
Q-learning with function approximation could diverge in the off-policy setting and the target network is a powerful technique to address this issue. In this manuscript, we examine…
Rethinking ValueDice: Does It Really Improve Performance?
Ziniu Li, Tian Xu, Yang Yu +1
Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvement…
On Generalization of Adversarial Imitation Learning and Beyond
Tian Xu, Ziniu Li, Yang Yu +1
Despite massive empirical evaluations, one of the fundamental questions in imitation learning is still not fully settled: does AIL (adversarial imitation learning) provably general…
Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization
Jing-Cheng Pang, Tian Xu, Shengyi Jiang +2
Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-makin…
Self-supervised learning for fast and scalable time series hyper-parameter tuning
Peiyi Zhang, Xiaodong Jiang, Ginger M Holt +4
Hyper-parameters of time series models play an important role in time series analysis. Slight differences in hyper-parameters might lead to very different forecast results for a gi…
Angular Embedding: A New Angular Robust Principal Component Analysis
Shenglan Liu, Yang Yu
As a widely used method in machine learning, principal component analysis (PCA) shows excellent properties for dimensionality reduction. It is a serious problem that PCA is sensiti…
Error Bounds of Imitating Policies and Environments
Tian Xu, Ziniu Li, Yang Yu
Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding…
QPLEX: Duplex Dueling Multi-Agent Q-Learning
Jianhao Wang, Zhizhou Ren, Terry Liu +2
We explore value-based multi-agent reinforcement learning (MARL) in the popular paradigm of centralized training with decentralized execution (CTDE). CTDE has an important concept,…
Local Neighbor Propagation Embedding
Shenglan Liu, Yang Yu
Manifold Learning occupies a vital role in the field of nonlinear dimensionality reduction and its ideas also serve for other relevant methods. Graph-based methods such as Graph Co…
Novelty-Prepared Few-Shot Classification
Chao Wang, Ruo-Ze Liu, Han-Jia Ye +1
Few-shot classification algorithms can alleviate the data scarceness issue, which is vital in many real-world problems, by adopting models pre-trained from abundant data in other d…
Improving Fictitious Play Reinforcement Learning with Expanding Models
Rong-Jun Qin, Jing-Cheng Pang, Yang Yu
Fictitious play with reinforcement learning is a general and effective framework for zero-sum games. However, using the current deep neural network models, the implementation of fi…