Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Liang, Yongyuan"'
Can we generate a control policy for an agent using just one demonstration of desired behaviors as a prompt, as effortlessly as creating an image from a textual description? In this paper, we present Make-An-Agent, a novel policy parameter generator
Externí odkaz:
http://arxiv.org/abs/2407.10973
Autor:
Pathmanathan, Pankayaraj, Chakraborty, Souradip, Liu, Xiangyu, Liang, Yongyuan, Huang, Furong
Publikováno v:
ICML 2024 Workshop MHFAIA
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization (PPO) has le
Externí odkaz:
http://arxiv.org/abs/2406.12091
Autor:
Ji, Tianying, Liang, Yongyuan, Zeng, Yan, Luo, Yu, Xu, Guowei, Guo, Jiawei, Zheng, Ruijie, Huang, Furong, Sun, Fuchun, Xu, Huazhe
The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rew
Externí odkaz:
http://arxiv.org/abs/2402.14528
In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust to adversarial attacks during test time. Current approaches largely rev
Externí odkaz:
http://arxiv.org/abs/2402.12673
Autor:
Zheng, Ruijie, Liang, Yongyuan, Wang, Xiyao, Ma, Shuang, Daumé III, Hal, Xu, Huazhe, Langford, John, Palanisamy, Praveen, Basu, Kalyan Shankar, Huang, Furong
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a
Externí odkaz:
http://arxiv.org/abs/2402.06187
Autor:
Xu, Guowei, Zheng, Ruijie, Liang, Yongyuan, Wang, Xiyao, Yuan, Zhecheng, Ji, Tianying, Luo, Yu, Liu, Xiaoyu, Yuan, Jiaxin, Hua, Pu, Li, Shuzhen, Ze, Yanjie, Daumé III, Hal, Huang, Furong, Xu, Huazhe
Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite its progress, current algorithms are still unsatisfactory in virtually every aspect of the performance such as sample efficiency, asymptotic performance, and th
Externí odkaz:
http://arxiv.org/abs/2310.19668
Autor:
Liang, Yongyuan, Sun, Yanchao, Zheng, Ruijie, Liu, Xiangyu, Eysenbach, Benjamin, Sandholm, Tuomas, Huang, Furong, McAleer, Stephen
Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are us
Externí odkaz:
http://arxiv.org/abs/2307.12062
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations. Therefore, it is crucial to train RL agents that are robust against any attacks with
Externí odkaz:
http://arxiv.org/abs/2210.05927
Autor:
Sun, Yanchao, Zheng, Ruijie, Hassanzadeh, Parisa, Liang, Yongyuan, Feizi, Soheil, Ganesh, Sumitra, Huang, Furong
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world application where noise and potential
Externí odkaz:
http://arxiv.org/abs/2206.10158
Evaluating the worst-case performance of a reinforcement learning (RL) agent under the strongest/optimal adversarial perturbations on state observations (within some constraints) is crucial for understanding the robustness of RL agents. However, find
Externí odkaz:
http://arxiv.org/abs/2106.05087