Related papers: Fast deep reinforcement learning using online adju…

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple state-of-the-art methods, we found vanilla experience…

Embodied agents face a fundamental limitation: once deployed in real-world environments, they cannot easily acquire new knowledge to improve task performance. In this paper, we propose Dejavu, a general post-deployment learning framework…

Self-adaptive systems frequently use tactics to perform adaptations. Tactic examples include the implementation of additional security measures when an intrusion is detected, or activating a cooling mechanism when temperature thresholds are…

Deep reinforcement learning enables an agent to capture user's interest through interactions with the environment dynamically. It has attracted great interest in the recommendation research. Deep reinforcement learning uses a reward…

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further…

Time-aware data valuation enhances training efficiency and model robustness, as early detection of harmful samples could prevent months of wasted computation. However, existing methods rely on model retraining or convergence assumptions or…

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…

Prioritized experience replay is a reinforcement learning technique whereby agents speed up learning by replaying useful past experiences. This usefulness is quantified as the expected gain from replaying the experience, a quantity often…

Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under…

This study explores the use of electroencephalography (EEG)-based brain wave monitoring to enable dynamic difficulty adjustment (DDA) in a virtual reality (VR) gaming environment. Using the Task Engagement Index (TEI) derived from frontal…

Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (ER) methods, especially those using TD-error prioritization,…

A central component of training in Reinforcement Learning (RL) is Experience: the data used for training. The mechanisms used to generate and consume this data have an important effect on the performance of RL algorithms. In this paper, we…

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function…

This paper presents a novel model-free Reinforcement Learning algorithm for learning behavior in continuous action, state, and goal spaces. The algorithm approximates optimal value functions using non-parametric estimators. It is able to…

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

The surrogate loss of variational autoencoders (VAEs) poses various challenges to their training, inducing the imbalance between task fitting and representation inference. To avert this, the existing strategies for VAEs focus on adjusting…

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning…

Modern scientific data acquisition generates petabytes of data that must be transferred to geographically distant computing clusters. Conventional tools either rely on preconfigured sessions, which are difficult to tune for users without…