相关论文: Hindsight Preference Replay Improves Preference-Co…

Learning from human involvement aims to incorporate the human subject to monitor and correct agent behavior errors. Although most interactive imitation learning methods focus on correcting the agent's action at the current state, they do…

This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal frequency. Such heterogeneity allows dense objectives to dominate learning, while sparse long-horizon rewards…

Hindsight Experience Replay (HER) is widely regarded as the state-of-the-art algorithm for achieving sample-efficient multi-goal reinforcement learning (RL) in robotic manipulation tasks with binary rewards. HER facilitates learning from…

Much of the success of single agent deep reinforcement learning (DRL) in recent years can be attributed to the use of experience replay memories (ERM), which allow Deep Q-Networks (DQNs) to be trained efficiently through sampling stored…

Multi-objective reinforcement learning (MORL) plays a pivotal role in addressing multi-criteria decision-making problems in the real world. The multi-policy (MP) based methods are widely used to obtain high-quality Pareto front…

Transformers have demonstrated exceptional in-context learning (ICL) capabilities, enabling applications across natural language processing, computer vision, and sequential decision-making. In reinforcement learning, ICL reframes learning…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction following tasks; however, it exhibits insufficient compliance…

Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving, which is increasingly applied in diverse driving scenarios. However, driving is a multi-attribute problem,…

Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods like Direct Preference Optimization (DPO) is a promising…

While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their limitations. To this end, residual policy learning (RPL)…

Adaptive context compression is vital for scaling Large Language Models (LLMs) to complex, multi-turn agent tasks. However, rule-based compression methods may discard task-critical nuances, while Reinforcement Learning (RL) approaches…

Due to their adaptability and mobility, Unmanned Aerial Vehicles (UAVs) are becoming increasingly essential for wireless network services, particularly for data harvesting tasks. In this context, Artificial Intelligence (AI)-based…

While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and…

In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses…

Hierarchical Reinforcement Learning (HRL) exploits temporally extended actions, or options, to make decisions from a higher-dimensional perspective to alleviate the sparse reward problem, one of the most challenging problems in…

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might…

Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single…

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this…

As multi-robot systems (MRS) are widely used in various tasks such as natural disaster response and social security, people enthusiastically expect an MRS to be ubiquitous that a general user without heavy training can easily operate.…