Related papers: Improving Transformer World Models for Data-Effici…
Despite the popularity of reinforcement learning (RL) in wireless networks, existing approaches that rely on model-free RL (MFRL) and model-based RL (MBRL) are data inefficient and short-sighted. Such RL-based solutions cannot generalize to…
Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the…
Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional…
World models learn general knowledge from videos and simulate experience for training behaviors in imagination, offering a path towards intelligent agents. However, previous world models have been unable to accurately predict object…
Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…
Vision-Language-Action (VLA) models enable embodied decision-making but rely heavily on imitation learning, leading to compounding errors and poor robustness under distribution shift. Reinforcement learning (RL) can mitigate these issues…
Sim-to-real transfer remains a significant challenge in robotics due to the discrepancies between simulated and real-world dynamics. Traditional methods like Domain Randomization often fail to capture fine-grained dynamics, limiting their…
Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…
World models are a fundamental component in model-based reinforcement learning (MBRL). To perform temporally extended and consistent simulations of the future in partially observable environments, world models need to possess long-term…
Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…
We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual…
Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In…
Simulation-to-reality reinforcement learning (RL) faces the critical challenge of reconciling discrepancies between simulated and real-world dynamics, which can severely degrade agent performance. A promising approach involves learning…
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…
The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by…
We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a…
Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…
Achieving quadruped robot locomotion across diverse and dynamic terrains presents significant challenges, primarily due to the discrepancies between simulation environments and real-world conditions. Traditional sim-to-real transfer methods…
A fundamental challenge in multi-task reinforcement learning (MTRL) is achieving sample efficiency in visual domains where tasks exhibit substantial heterogeneity in both observations and dynamics. Model-based reinforcement learning offers…
The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…