相关论文: DreamerV3-XP: Optimizing exploration through uncer…

Numerous machine learning problems require an exploration basis - a mechanism to explore the action space. We define a novel geometric notion of exploration basis with low variance, called volumetric spanners, and give efficient algorithms…

Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore), a structured…

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for…

Numerous real-world control problems involve dynamics and objectives affected by unobservable hidden parameters, ranging from autonomous driving to robotic manipulation, which cause performance degradation during sim-to-real transfer. To…

This work pushes the boundaries of learning-based methods in autonomous robot exploration in terms of environmental scale and exploration efficiency. We present HEADER, an attention-based reinforcement learning approach with hierarchical…

We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks. To the best of our knowledge, MEM is the first approach that combines multi-view representation learning and intrinsic reward-driven exploration…

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show…

Top-performing Model-Based Reinforcement Learning (MBRL) agents, such as Dreamer, learn the world model by reconstructing the image observations. Hence, they often fail to discard task-irrelevant details and struggle to handle visual…

Uncertainty is widely acknowledged as an engaging gameplay element but rarely used in exergames. In this research, we explore the role of uncertainty in exergames and introduce three uncertain elements (false-attacks, misses, and critical…

In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration. While the computation of many intrinsic rewards relies on estimating variational posteriors using neural network…

Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs)…

With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training stability. As a time-efficient diffusion model, although…

3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce…

Experience replay is widely used to improve learning efficiency in reinforcement learning by leveraging past experiences. However, existing experience replay methods, whether based on uniform or prioritized sampling, often suffer from low…

Recently, various pre-training methods have been introduced in vision-based Reinforcement Learning (RL). However, their generalization ability remains unclear due to evaluations being limited to in-distribution environments and non-unified…

Human environments are often regulated by explicit and complex rulesets. Integrating Reinforcement Learning (RL) agents into such environments motivates the development of learning mechanisms that perform well in rule-dense and…

Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined…

Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among…

Fine-tuning text-to-image diffusion models to maximize rewards has proven effective for enhancing model performance. However, reward fine-tuning methods often suffer from slow convergence due to online sample generation. Therefore,…

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning…