Related papers: Advancing Autonomous VLM Agents via Variational Su…

Powered by deep representation learning, reinforcement learning (RL) provides an end-to-end learning framework capable of solving self-driving (SD) tasks without manual designs. However, time-varying nonstationary environments cause…

Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception, suboptimal multimodal fusion, and instability in reinforcement learning. To bridge…

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward…

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

We propose a reinforcement learning (RL) framework under a broad class of risk objectives, characterized by convex scoring functions. This class covers many common risk measures, such as variance, Expected Shortfall, entropic Value-at-Risk,…

Deep Reinforcement Learning (DRL) has shown great potential in enabling robots to find certain objects (e.g., `find a fridge') in environments like homes or schools. This task is known as Object-Goal Navigation (ObjectNav). DRL methods are…

Reinforcement learning (RL) has proven highly effective in eliciting the reasoning capabilities of large language models (LLMs). Inspired by this success, recent studies have explored applying similar techniques to vision-language models…

Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through interaction. However,…

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Navigating and understanding complex and unknown environments autonomously demands more than just basic perception and movement from embodied agents. Truly effective exploration requires agents to possess higher-level cognitive abilities,…

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…

Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation…

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning…

Reinforcement learning (RL) has emerged as a critical paradigm for post-training Vision-Language-Action (VLA) models, enabling embodied agents to adapt and improve through environmental interaction. However, existing RL frameworks for VLAs…

Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn…

As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learning (RL) has emerged as a promising paradigm for training MLLM agents on dynamic GUI tasks,…

Reinforcement Learning (RL) is a potent tool for sequential decision-making and has achieved performance surpassing human capabilities across many challenging real-world tasks. As the extension of RL in the multi-agent system domain,…

Traffic congestion remains a major challenge for urban transportation, leading to significant economic and environmental impacts. Traffic Signal Control (TSC) is one of the key measures to mitigate congestion, and recent studies have…

Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals. Recent advances in large multimodal models (LMMs) enable flexible expression of such intentions through…