Related papers: Self-Improving World Modelling with Latent Actions
While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive…
Recently, AI systems have made remarkable progress in various tasks. Deep Reinforcement Learning(DRL) is an effective tool for agents to learn policies in low-level state spaces to solve highly complex tasks. Researchers have introduced…
Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflows, fundamentally limiting scalability to…
Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynamics model. In many instances of MBRL and MPC, this model is assumed to be stationary and is…
Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement…
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-based reinforcement learning (MBRL) mitigates this by building…
Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…
Dynamics model learning deals with the task of inferring unknown dynamics from measurement data and predicting the future behavior of the system. A typical approach to address this problem is to train recurrent models. However, predictions…
Traditional reinforcement learning (RL)-based learning approaches for wireless networks rely on expensive trial-and-error mechanisms and real-time feedback based on extensive environment interactions, which leads to low data efficiency and…
Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a…
Despite remarkable progress in driving world models, their potential for autonomous systems remains largely untapped: the world models are mostly learned for world simulation and decoupled from trajectory planning. While recent efforts aim…
In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based solely on a dataset of historical interactions with the environment. The ability to train RL policies offline can greatly expand the applicability…
Reinforcement learning has been shown to improve the performance of large language models. However, traditional approaches like RLHF or RLAIF treat the problem as single-step. As focus shifts toward more complex reasoning and agentic tasks,…
The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…
Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden "trap states" --…
Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…
Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric…
We study the use of inverse reinforcement learning (IRL) as a tool for the recognition of agents' behavior on the basis of observation of their sequential decision behavior interacting with the environment. We model the problem faced by the…
Learning the optimal policy from a random network initialization is the theme of deep Reinforcement Learning (RL). As the scale of DRL training increases, treating DRL policy network weights as a new data modality and exploring the…
Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable…