相关论文: Learning from Visual Observation via Offline Pretr…

Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially…

The paper proposes the use of structured neural networks for reinforcement learning based nonlinear adaptive control. The focus is on partially observable systems, with separate neural networks for the state and feedforward observer and the…

This paper focuses on inverse reinforcement learning (IRL) to enable safe and efficient autonomous navigation in unknown partially observable environments. The objective is to infer a cost function that explains expert-demonstrated…

Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However,…

In early childhood education, accurately detecting collaborative and behavioral engagement is essential to foster meaningful learning experiences. This paper presents an AI driven approach that leverages Vision Transformers (ViTs) to…

In visual Reinforcement Learning (RL), upstream representation learning largely determines the effect of downstream policy learning. Employing auxiliary tasks allows the agent to enhance visual representation in a targeted manner, thereby…

We examine the problem of transferring a policy learned in a source environment to a target environment with different dynamics, particularly in the case where it is critical to reduce the amount of interaction with the target environment…

Evolutions in the world, such as water pouring or ice melting, happen regardless of being observed. Video world models generate "worlds" via 2D frame observations. Can these generated "worlds" evolve regardless of observation? To probe this…

In robot learning, Vision Transformers (ViTs) are standard for visual perception, yet most methods discard valuable information by using only the final layer's features. We argue this provides an insufficient representation and propose the…

Recent vision-language-action (VLA) models for multi-task robot manipulation often rely on fixed camera setups and shared visual encoders, which limit their performance under occlusions and during cross-task transfer. To address these…

In partially observable (PO) environments, deep reinforcement learning (RL) agents often suffer from unsatisfactory performance, since two problems need to be tackled together: how to extract information from the raw observations to solve…

Micro-expressions are involuntary facial movements that cannot be consciously controlled, conveying subtle cues with substantial real-world applications. The analysis of micro-expressions generally involves two main tasks: spotting…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Large models based on the Transformer architecture are susceptible to extreme-token phenomena, such as attention sinks and value-state drains. These issues, which degrade model performance, quantization fidelity, and interpretability, arise…

Reinforcement Learning (RL), among other learning-based methods, represents powerful tools to solve complex robotic tasks (e.g., actuation, manipulation, navigation, etc.), with the need for real-world data to train these systems as one of…

This work leverages adaptive social learning to estimate partially observable global states in multi-agent reinforcement learning (MARL) problems. Unlike existing methods, the proposed approach enables the concurrent operation of social…

Offline reinforcement learning (RL) allows learning sequential behavior from fixed datasets. Since offline datasets do not cover all possible situations, many methods collect additional data during online fine-tuning to improve performance.…

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

In everyday life collaboration tasks between human operators and robots, the former necessitate simple ways for programming new skills, the latter have to show adaptive capabilities to cope with environmental changes. The joint use of…