Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Ji, Tianying"'
Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only consider subgoal
Externí odkaz:
http://arxiv.org/abs/2406.18053
Autor:
Zhou, Hantao, Ji, Tianying, Sommerhalder, Lukas, Goerner, Michael, Hendrich, Norman, Zhang, Jianwei, Sun, Fuchun, Xu, Huazhe
Minigolf is an exemplary real-world game for examining embodied intelligence, requiring challenging spatial and kinodynamic understanding to putt the ball. Additionally, reflective reasoning is required if the feasibility of a challenge is not ensure
Externí odkaz:
http://arxiv.org/abs/2406.10157
Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or dynamics shift
Externí odkaz:
http://arxiv.org/abs/2405.19080
Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally exploit the
Externí odkaz:
http://arxiv.org/abs/2405.18520
Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominan
Externí odkaz:
http://arxiv.org/abs/2405.12001
Model Predictive Control (MPC) has exhibited remarkable capabilities in optimizing objectives and meeting constraints. However, the substantial computational burden associated with solving the Optimal Control Problem (OCP) at each triggering instant
Externí odkaz:
http://arxiv.org/abs/2403.01265
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
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:
Niu, Haoyi, Ji, Tianying, Liu, Bingqi, Zhao, Haocheng, Zhu, Xiangyu, Zheng, Jianying, Huang, Pengfei, Zhou, Guyue, Hu, Jianming, Zhan, Xianyuan
Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can suffer from
Externí odkaz:
http://arxiv.org/abs/2309.12716
Learning high-quality $Q$-value functions plays a key role in the success of many modern off-policy deep reinforcement learning (RL) algorithms. Previous works primarily focus on addressing the value overestimation issue, an outcome of adopting funct
Externí odkaz:
http://arxiv.org/abs/2306.02865