Related papers: Exploration and Anti-Exploration with Distribution…

Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters. In this work, we introduce…

Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand,…

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches…

Despite the recent success of deep neural networks, there remains a need for effective methods to enhance domain generalization using vision transformers. In this paper, we propose a novel domain generalization technique called Robust…

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…

We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND…

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…

The reward model (RM), as the core component of reinforcement learning from human feedback (RLHF) for large language models (LLMs), responsible for providing reward signals to generated responses. However, the mainstream discriminative…

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have shown the effectiveness…

The goal of an offline reinforcement learning (RL) algorithm is to learn optimal polices using historical (offline) data, without access to the environment for online exploration. One of the main challenges in offline RL is the distribution…

Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous…

Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…

Network slicing-based communication systems can dynamically and efficiently allocate resources for diversified services. However, due to the limitation of the network interface on channel access and the complexity of the resource…

To classify in-distribution samples, deep neural networks explore strongly label-related information and discard weakly label-related information according to the information bottleneck. Out-of-distribution samples drawn from distributions…

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world…

Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making…

Network slicing is born as an emerging business to operators, by allowing them to sell the customized slices to various tenants at different prices. In order to provide better-performing and cost-efficient services, network slicing involves…

Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to…

Portfolio optimization is essential for balancing risk and return in financial decision-making. Deep Reinforcement Learning (DRL) has stood out as a cutting-edge tool for portfolio optimization that learns dynamic asset allocation using…