Related papers: Virtual Replay Cache
Mini-batch training is a cornerstone of modern deep learning, offering computational efficiency and scalability for training complex architectures. However, existing deep subspace clustering (DSC) methods, which typically combine an…
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…
Visual attention serves as a means of feature selection mechanism in the perceptual system. Motivated by Broadbent's leaky filter model of selective attention, we evaluate how such mechanism could be implemented and affect the learning…
Deep reinforcement learning has emerged as a powerful tool for a variety of learning tasks, however deep nets typically exhibit forgetting when learning multiple tasks in sequence. To mitigate forgetting, we propose an experience replay…
We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value…
Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data collected in previous iterations to accelerate policy optimization. Classical experience replay treats all past observations uniformly…
Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, RAG introduces long…
Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…
Learning good feature representations is important for deep reinforcement learning (RL). However, with limited experience, RL often suffers from data inefficiency for training. For un-experienced or less-experienced trajectories (i.e.,…
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…
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…
Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is…
Replay strategies are Continual Learning techniques which mitigate catastrophic forgetting by keeping a buffer of patterns from previous experiences, which are interleaved with new data during training. The amount of patterns stored in the…
To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce…
Contrastive learning has been applied successfully to learn vector representations of text. Previous research demonstrated that learning high-quality representations benefits from batch-wise contrastive loss with a large number of…
Due to the fluctuation of throughput under various network conditions, how to choose a proper bitrate adaptively for real-time video streaming has become an upcoming and interesting issue. Recent work focuses on providing high video…
Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…
In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games. The next step of intelligent agents would be able to generalize between tasks, and using prior…
Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay…
We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a…