7 accepted papers
Offline reinforcement learning (RL) faces a critical challenge of overestimating the value of out-of-distribution (OOD) actions. Existing methods mitigate this issue by penalizing unseen samples, yet they fail to accurately identify OOD actions and may suppress beneficial exploration beyond the beh…
Value function factorization is widely used in cooperative multi-agent reinforcement learning (MARL). Existing approaches often impose monotonicity constraints between the joint action value and individual action values to enable decentralized execution. However, such constraints limit the expressiv…
Commonly used asymptotically convergent sampling algorithms (SBP) often utilize the Informed Set (IS) to enhance sampling efficiency. However, IS typically requires obtaining a low-cost solution first, which is challenging when narrow passages are present in the environment. To address the narrow pa
Existing context-based offline meta-reinforcement learning (COMRL) methods primarily focus on task representation learning and given-context adaptation performance. They often assume that the adaptation context is collected using task-specific behavior policies or through multiple rounds of collecti…
A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image reconstruction due to concerns about exacerbating overfitting to task…
Safety is one of the main challenges in applying reinforcement learning to tasks in realistic environments. To ensure safety during and after the training process, existing methods tend to adopt overly conservative policies to avoid unsafe situations. However, an overly conservative policy severely
Designing and deriving effective model-based reinforcement learning (MBRL) algorithms with a performance improvement guarantee is challenging, mainly attributed to the high coupling between model learning and policy optimization. Many prior methods that rely on return discrepancy to guide model lear…