.png){kind=icon}
返回
Data-efficient model-based reinforcement learning with trajectory discrimination
.png){kind=icon}
OA
AI
DOI：10.1007/s40747-023-01247-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep reinforcement learning has always been used to solve high-dimensional complex sequential decision problems. However, one of the biggest challenges for reinforcement learning is sample efficiency, especially for high-dimensional complex problems. Model-based reinforcement learning can solve the problem with a learned world model, but the performance is limited by the imperfect world model, so it usually has worse approximate performance than model-free reinforcement learning. In this paper, we propose a novel model-based reinforcement learning algorithm called World Model with Trajectory Discrimination (WMTD). We learn the representation of temporal dynamics information by adding a trajectory discriminator to the world model, and then compute the weight of state value estimation based on the trajectory discriminator to optimize the policy. Specifically, we augment the trajectories to generate negative samples and train a trajectory discriminator that shares the feature extractor with the world model. Experimental results demonstrate that our method improves the sample efficiency and achieves state-of-the-art performance on DeepMind control tasks.
Keyword:
Reinforcement learning
Deep learning
Continuous control task
World model
期刊
IF:
4.6
论文数:
2.1K
被引数:
6.6K
机构
查看更多机构
引用论文
.png){kind=icon}
Finite-time control of discrete-time semi-Markov jump linear systems: A self-triggered MPC approach离散半马尔可夫跳变线性系统的有限时间控制: 一种自触发MPC方法
PREAI
分享收藏
Evolutionary Multi-Objective Reinforcement Learning Based Trajectory Control and Task Offloading in UAV-Assisted Mobile Edge Computing基于进化多目标强化学习的无人机辅助移动边缘计算轨迹控制与任务卸载OAAI
OAAI分享收藏 没有更多内容