相关论文: MONA: Myopic Optimization with Non-myopic Approval…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF…

Traditional reinforcement learning (RL) assumes the agents make decisions based on Markov decision processes (MDPs) with one-step transition models. In many real-world applications, such as energy management and stock investment, agents can…

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate…

Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant…

In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learned policy either converges to non-optimal performance with…

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF), yet they remain vulnerable to reward hacking. Existing attacks mainly operate within the semantic space, constructing…

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses…

Random access schemes in modern wireless communications are generally based on the framed-ALOHA (f-ALOHA), which can be optimized by flexibly organizing devices' transmission and re-transmission. However, this optimization is generally…

Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local…

One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network. While this…

An important current challenge in Human-Robot Interaction (HRI) is to enable robots to learn on-the-fly from human feedback. However, humans show a great variability in the way they reward robots. We propose to address this issue by…

Humanoid robots must master numerous tasks with sparse rewards, posing a challenge for reinforcement learning (RL). We propose a method combining RL and automated planning to address this. Our approach uses short goal-conditioned policies…

Gradient-based optimizers are highly sensitive to design choices in their adaptive learning rate mechanisms. To address this limitation, we introduce POP, a meta-learned Reinforcement Learning (RL) policy that predicts adaptive learning…

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation.…

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Reward design is a fundamental problem in reinforcement learning (RL). A misspecified or poorly designed reward can result in low sample efficiency and undesired behaviors. In this paper, we propose the idea of programmatic reward design,…

A misspecified reward can degrade sample efficiency and induce undesired behaviors in reinforcement learning (RL) problems. We propose symbolic reward machines for incorporating high-level task knowledge when specifying the reward signals.…