8 papers · 1 filter
LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models
Mingqi Yuan, Xiaoquan Sun, Shihao Luo +1
Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream under strict single-pass c…
Vision Transformers that Never Stop Learning
Caihao Sun, Mingqi Yuan, Shiyuan Wang +1
Loss of plasticity refers to the progressive inability of a model to adapt to new tasks and poses a fundamental challenge for continual learning. While this phenomenon has been ext…
Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning
Qi Wang, Mian Wu, Yuyang Zhang +7
Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Des…
Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
Mingqi Yuan, Qi Wang, Guozheng Ma +8
Developing lifelong learning agents is crucial for artificial general intelligence (AGI). However, deep reinforcement learning (RL) systems often suffer from plasticity loss, where…
ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
Mingqi Yuan, Bo Li, Xin Jin +1
Hyperparameter optimization (HPO) is a billion-dollar problem in machine learning, which significantly impacts the training efficiency and model performance. However, achieving eff…
Deep Reinforcement Learning with Hybrid Intrinsic Reward Model
Mingqi Yuan, Bo Li, Xin Jin +1
Intrinsic reward shaping has emerged as a prevalent approach to solving hard-exploration and sparse-rewards environments in reinforcement learning (RL). While single intrinsic rewa…
Adaptive Data Exploitation in Deep Reinforcement Learning
Mingqi Yuan, Bo Li, Xin Jin +1
We introduce ADEPT: Adaptive Data ExPloiTation, a simple yet powerful framework to enhance the **data efficiency** and **generalization** in deep reinforcement learning (RL). Speci…
RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning
Mingqi Yuan, Roger Creus Castanyer, Bo Li +3
Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the si…