Open-world survival games pose significant challenges for AI algorithms due to their multi-
tasking, deep exploration, and goal prioritization requirements. Despite reinforcement …

We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents.
AgentKit offers a unified framework for explicitly constructing a complex" thought process" …

Existing grasp prediction approaches are mostly based on offline learning, while, ignored
the exploratory grasp learning during online adaptation to new picking scenarios, ie, unseen …

This paper introduces an effective and practical step toward approximate Bayesian
inference in on-policy actor-critic deep reinforcement learning. This step manifests as three …

Despite recent progress in offline learning, these methods are still trained and tested on the
same environment. In this paper, we compare the generalization abilities of widely used …

Reinforcement learning agents may sometimes develop habits that are effective only when
specific policies are followed. After an initial exploration phase in which agents try out …

While large language models (LLMs) have been increasingly deployed across tasks in
language understanding and interactive decision-making, their impressive performance is …

Effective interlocutors account for the uncertain goals, beliefs, and emotions of others. But
even the best human conversationalist cannot perfectly anticipate the trajectory of a …

Despite the recent progress in offline reinforcement learning (RL) algorithms, agents are
usually trained and tested on the same environment. In this paper, we perform an in-depth …

We present $\varepsilon $-retrain, an exploration strategy designed to encourage a
behavioral preference while optimizing policies with monotonic improvement guarantees. To …