Applying Reinforcement Learning (RL) to sequence generation models enables the direct
optimization of long-term rewards (\textit {eg,} BLEU and human feedback), but typically …

The sparse reward problem stands as a significant challenge in the field of reinforcement
learning. Hindsight Experience Replay (HER) addresses this by goal relabeling, allowing …

Training a multi-agent reinforcement learning (MARL) model with a sparse reward is
generally difficult because numerous combinations of interactions among agents induce a …

Efficient reinforcement learning (RL) involves a trade-off between" exploitative" actions that
maximise expected reward and" explorative'" ones that sample unvisited states. To …

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 …

Efficient reinforcement learning (RL) involves a trade-off between" exploitative" actions that
maximise expected reward and``explorative" ones that lead to the visitation of" novel" states …