303 citations · 533 across the 92 of their papers we have counts for
39 papers · 1 filter
Debiased Model-based Representations for Sample-efficient Continuous Control
Jiafei Lyu, Zichuan Lin, Scott Fujimoto +5
Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic lear…
Temporal Difference Learning with Constrained Initial Representations
Jiafei Lyu, Jingwen Yang, Zhongjian Qiao +5
Recently, there have been numerous attempts to enhance the sample efficiency of off-policy reinforcement learning (RL) agents when interacting with the environment, including archi…
Guided Policy Optimization under Partial Observability
Yueheng Li, Guangming Xie, Zongqing Lu
Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, suc…
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Jiafei Lyu, Kang Xu, Jiacheng Xu +6
We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-…
SELU: Self-Learning Embodied MLLMs in Unknown Environments
Boyu Li, Haobin Jiang, Ziluo Ding +4
Recently, multimodal large language models (MLLMs) have demonstrated strong visual understanding and decision-making capabilities, enabling the exploration of autonomously improvin…
MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
Junpeng Yue, Xinrun Xu, Börje F. Karlsson +1
MLLM agents demonstrate potential for complex embodied tasks by retrieving multimodal task-relevant trajectory data. However, current retrieval methods primarily focus on surface-l…
Cross-Domain Policy Adaptation by Capturing Representation Mismatch
Jiafei Lyu, Chenjia Bai, Jingwen Yang +2
It is vital to learn effective policies that can be transferred to different domains with dynamics discrepancies in reinforcement learning (RL). In this paper, we consider dynamics…
SEABO: A Simple Search-Based Method for Offline Imitation Learning
Jiafei Lyu, Xiaoteng Ma, Le Wan +3
Offline reinforcement learning (RL) has attracted much attention due to its ability in learning from static offline datasets and eliminating the need of interacting with the enviro…
Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence
Jiafei Lyu, Le Wan, Xiu Li +1
Recently, there are many efforts attempting to learn useful policies for continuous control in visual reinforcement learning (RL). In this scenario, it is important to learn a gene…
LLaMA Rider: Spurring Large Language Models to Explore the Open World
Yicheng Feng, Yuxuan Wang, Jiazheng Liu +2
Recently, various studies have leveraged Large Language Models (LLMs) to help decision-making and planning in environments, and try to align the LLMs' knowledge with the world cond…
Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
Bohan Zhou, Ke Li, Jiechuan Jiang +1
Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either on…
Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation
Wanpeng Zhang, Yilin Li, Boyu Yang +1
In real-world scenarios, the application of reinforcement learning is significantly challenged by complex non-stationarity. Most existing methods attempt to model changes in the en…
Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse
Jiafei Lyu, Le Wan, Zongqing Lu +1
Sample efficiency is one of the most critical issues for online reinforcement learning (RL). Existing methods achieve higher sample efficiency by adopting model-based methods, Q-en…
Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks
Haoqi Yuan, Chi Zhang, Hongcheng Wang +4
We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinf…
Reinforcement Learning Friendly Vision-Language Model for Minecraft
Haobin Jiang, Junpeng Yue, Hao Luo +2
One of the essential missions in the AI research community is to build an autonomous embodied agent that can achieve high-level performance across a wide spectrum of tasks. However…
Model-Based Decentralized Policy Optimization
Hao Luo, Jiechuan Jiang, Zongqing Lu
Decentralized policy optimization has been commonly used in cooperative multi-agent tasks. However, since all agents are updating their policies simultaneously, from the perspectiv…
Learning Multi-Object Positional Relationships via Emergent Communication
Yicheng Feng, Boshi An, Zongqing Lu
The study of emergent communication has been dedicated to interactive artificial intelligence. While existing work focuses on communication about single objects or complex image sc…
Best Possible Q-Learning
Jiechuan Jiang, Zongqing Lu
Fully decentralized learning, where the global information, i.e., the actions of other agents, is inaccessible, is a fundamental challenge in cooperative multi-agent reinforcement…
A Survey on Transformers in Reinforcement Learning
Wenzhe Li, Hao Luo, Zichuan Lin +3
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings. Recently, a similar surge of using Transformers has appeared in…
State Advantage Weighting for Offline RL
Jiafei Lyu, Aicheng Gong, Le Wan +2
We present state advantage weighting for offline reinforcement learning (RL). In contrast to action advantage that we commonly adopt in QSA learning, we leverage state adv…
Decentralized Policy Optimization
Kefan Su, Zongqing Lu
The study of decentralized learning or independent learning in cooperative multi-agent reinforcement learning has a history of decades. Recently empirical studies show that indepen…
Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning
Ziluo Ding, Wanpeng Zhang, Junpeng Yue +3
We investigate the use of natural language to drive the generalization of policies in multi-agent settings. Unlike single-agent settings, the generalization of policies should also…
Multi-Agent Automated Machine Learning
Zhaozhi Wang, Kefan Su, Jian Zhang +4
In this paper, we propose multi-agent automated machine learning (MA2ML) with the aim to effectively handle joint optimization of modules in automated machine learning (AutoML). MA…
More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization
Jiangxing Wang, Deheng Ye, Zongqing Lu
In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for t…