Related papers: Unsupervised Visual Attention and Invariance for R…
Variational inference (VI) is a specific type of approximate Bayesian inference that approximates an intractable posterior distribution with a tractable one. VI casts the inference problem as an optimization problem, more specifically, the…
Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…
Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs) still lack. Earlier reinforcement-learning (RL) efforts…
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like…
Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is…
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}.…
Recent works in self-supervised learning have shown impressive results on single-object images, but they struggle to perform well on complex multi-object images as evidenced by their poor visual grounding. To demonstrate this concretely, we…
Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform…
Many vision-language tasks can be reduced to the problem of sequence prediction for natural language output. In particular, recent advances in image captioning use deep reinforcement learning (RL) to alleviate the "exposure bias" during…
Generalization is a pivotal challenge for agents following natural language instructions. To approach this goal, we leverage a vision-language model (VLM) for visual grounding and transfer its vision-language knowledge into reinforcement…
Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming…
Recent research tries to extend image restoration capabilities from human perception to machine perception, thereby enhancing the performance of high-level vision tasks in degraded environments. These methods, primarily based on supervised…
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…
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challenge in unsupervised RL is to extract behaviors that…
This work proposes a novel model-free Reinforcement Learning (RL) agent that is able to learn how to complete an unknown task having access to only a part of the input observation. We take inspiration from the concepts of visual attention…
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…
The recent success in deep learning has lead to various effective representation learning methods for videos. However, the current approaches for video representation require large amount of human labeled datasets for effective learning. We…
Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\text{inv}}$ where the conditional distribution $Y…
Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent's decision-making process is generally not transparent. The lack of interpretability hinders the applicability…