Related papers: Sophisticated Learning: A novel algorithm for acti…
Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fail to capture quality differences among trajectories…
Meta-learning algorithms for active learning are emerging as a promising paradigm for learning the ``best'' active learning strategy. However, current learning-based active learning approaches still require sufficient training data so as to…
Re-training a deep learning model each time a single data point receives a new label is impractical due to the inherent complexity of the training process. Consequently, existing active learning (AL) algorithms tend to adopt a batch-based…
Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for…
Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning…
Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a…
Branching Time Active Inference (Champion et al., 2021b,a) is a framework proposing to look at planning as a form of Bayesian model expansion. Its root can be found in Active Inference (Friston et al., 2016; Da Costa et al., 2020; Champion…
Accelerating the inference speed of CNNs is critical to their deployment in real-world applications. Among all the pruning approaches, those implementing a sparsity learning framework have shown to be effective as they learn and prune the…
Many robot manipulation skills can be represented with deterministic characteristics and there exist efficient techniques for learning parameterized motor plans for those skills. However, one of the active research challenge still remains…
Handling heterogeneity and unpredictability are two core problems in pervasive computing. The challenge is to seamlessly integrate devices with varying computational resources in a dynamic environment to form a cohesive system that can…
Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…
Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples that are known to be semantically akin, i.e. positive views. Requiring…
Sim-to-real discrepancies hinder learning-based policies from achieving high-precision tasks in the real world. While Domain Randomization (DR) is commonly used to bridge this gap, it often relies on heuristics and can lead to overly…
We seek to align agent policy with human expert behavior in a reinforcement learning (RL) setting, without any prior knowledge about dynamics, reward function, and unsafe states. There is a human expert knowing the rewards and unsafe states…
In this paper, we explore how we can build upon the data and models of Internet images and use them to adapt to robot vision without requiring any extra labels. We present a framework called Self-supervised Embodied Active Learning (SEAL).…
Humans learn to play video games significantly faster than the state-of-the-art reinforcement learning (RL) algorithms. People seem to build simple models that are easy to learn to support planning and strategic exploration. Inspired by…
A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. Many models such as SVM, random forest, and deep neural nets have been proposed and achieved great success.…
Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional approach of considering the same fixed action space in…
Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how…
How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. Without control over the…