The ability to continuously acquire new knowledge and skills is crucial for autonomous
agents. Existing methods are typically based on either fixed-size models that struggle to …

One of the key challenges in deploying RL to real-world applications is to adapt to variations
of unknown environment contexts, such as changing terrains in robotic tasks and fluctuated …

Abstract We introduce Dynamic Contextual Markov Decision Processes (DCMDPs), a novel
reinforcement learning framework for history-dependent environments that generalizes the …

Cooperative multi-agent reinforcement learning (MARL), where agents coordinates with
teammate (s) for a shared goal, may sustain non-stationary caused by the policy change of …

Static machine learning methods in gesture recognition assume that training and test data
come from the same underlying distribution. However, in real-world applications involving …

Continual reinforcement learning aims to sequentially learn a variety of tasks, retaining the
ability to perform previously encountered tasks while simultaneously developing new …

The reliable deployment of deep reinforcement learning in real-world settings requires the
ability to generalize across a variety of conditions, including both in-distribution scenarios …

Recent research has turned to Reinforcement Learning (RL) to solve challenging decision
problems, as an alternative to hand-tuned heuristics. RL can learn good policies without the …

Continual reinforcement learning aims to sequentially learn a variety of tasks, retaining the
ability to perform previously encountered tasks while simultaneously developing new …

This work explores" Subspaces of Policies for Deep Reinforcement Learning," introducing
an innovative approach to address adaptability and generalization challenges in deep …