相关论文: HALO: Human Preference Aligned Offline Reward Lear…

Reinforcement learning can enable robots to navigate to distant goals while optimizing user-specified reward functions, including preferences for following lanes, staying on paved paths, or avoiding freshly mowed grass. However, online…

Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, previous pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are…

Robots often need to learn the human's reward function online, during the current interaction. This real-time learning requires fast but approximate learning rules: when the human's behavior is noisy or suboptimal, current approximations…

We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-agnostic options in a self-supervised manner while jointly learning to utilize them to solve sparse-reward tasks. Unlike current hierarchical RL approaches…

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

Conversational human-likeness plays a central role in human-AI interaction, yet it has remained difficult to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised…

Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the…

We present a novel outdoor navigation algorithm to generate stable and efficient actions to navigate a robot to reach a goal. We use a multi-stage training pipeline and show that our approach produces policies that result in stable and…

Reinforcement Learning from Human Feedback (RLHF) is currently the leading approach for aligning large language models with human preferences. Typically, these models rely on extensive offline preference datasets for training. However,…

Humanoid robots deployed in real-world scenarios often need to carry unknown payloads, which introduce significant mismatch and degrade the effectiveness of simulation-to-reality reinforcement learning methods. To address this challenge, we…

Reinforcement Learning from Human Feedback (RLHF) plays a crucial role in aligning large language models (LLMs) with human values and preferences. However, the quality and stability of the trained reward model largely determine the final…

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based…

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each…

Proximal Policy Optimization (PPO)-based reinforcement learning from human feedback (RLHF) is a widely adopted paradigm for aligning large language models (LLMs) with human preferences. However, its training pipeline suffers from…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second,…

Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise…

Aligning AI systems with human preferences typically suffers from the infamous reward hacking problem, where optimization of an imperfect reward model leads to undesired behaviors. In this paper, we investigate reward hacking in offline…

The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Today navigation applications (e.g., Waze and Google Maps) enable human users to learn and share the latest traffic observations, yet such information sharing simply aids selfish users to predict and choose the shortest paths to jam each…