We observe that current state-of-the-art (SOTA) methods suffer from the performance
imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While …

Multi-task reinforcement learning (MTRL) has emerged as a challenging problem to reduce
the computational cost of reinforcement learning and leverage shared features among tasks …

Multi-task reinforcement learning (RL) faces the significant challenge of varying task
difficulties, often leading to negative transfer when simpler tasks overshadow the learning of …

Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the
generalization of a robot, enabling it to perform multiple tasks concurrently. However, the …

Multi-task reinforcement learning is promising to alleviate the low sample efficiency and high
computation cost of reinforcement learning algorithms. However, current methods mostly …

In the field of multi-task reinforcement learning, the modular principle, which involves
specializing functionalities into different modules and combining them appropriately, has …

Multi-goal reinforcement learning (RL) aims to qualify the agent to accomplish multi-goal
tasks, which is of great importance in learning scalable robotic manipulation skills. However …

The ability to leverage shared behaviors between tasks is critical for sample-efficient multi-
task reinforcement learning (MTRL). While prior methods have primarily explored parameter …

Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating
deep neural networks in learning representations from the input to RL. However, the …

The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can
be applied to a set of different tasks. Sharing parameters allows us to take advantage of the …