相关论文: Dual-Granularity Contrastive Reward via Generated …

Balancing multiple objectives is critical for user satisfaction in modern recommender and search systems, yet current Multi-Task Fusion (MTF) methods rely on static, manually-tuned weights that fail to capture individual user intent. While…

We study the problem of sample efficient reinforcement learning, where prior data such as demonstrations are provided for initialization in lieu of a dense reward signal. A natural approach is to incorporate an imitation learning objective,…

Reward function design and exploration time are arguably the biggest obstacles to the deployment of reinforcement learning (RL) agents in the real world. In many real-world tasks, designing a reward function takes considerable hand…

We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only…

Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way. In this paper, we address three critical challenges for this task in a reinforcement learning…

To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation…

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely…

Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a single episode. While diffusion-based planners enable flexible trajectory generation,…

Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and a general class of such properties is the multiple reward…

Synthetic data is crucial for advancing autonomous driving (AD) systems, yet current state-of-the-art video generation models, despite their visual realism, suffer from subtle geometric distortions that limit their utility for downstream…

Rewards play a crucial role in reinforcement learning. To arrive at the desired policy, the design of a suitable reward function often requires significant domain expertise as well as trial-and-error. Here, we aim to minimize the effort…

The objective of many real-world tasks is complex and difficult to procedurally specify. This makes it necessary to use reward or imitation learning algorithms to infer a reward or policy directly from human data. Existing benchmarks for…

Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward learning, where reward functions are inferred from human feedback rather than manually specified.…

Reinforcement Learning (RL) has become a key approach for enhancing the reasoning capabilities of large language models. However, prevalent RL approaches like proximal policy optimization and group relative policy optimization suffer from…

Applying reinforcement learning (RL) to sparse reward domains is notoriously challenging due to insufficient guiding signals. Common RL techniques for addressing such domains include (1) learning from demonstrations and (2) curriculum…

Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions…

Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which…

Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense…

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…

While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend…