Related papers: RLx2: Training a Sparse Deep Reinforcement Learnin…

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Reinforcement Learning (RL) is a well-established framework for sequential decision-making in complex environments. However, state-of-the-art Deep RL (DRL) algorithms typically require large training datasets and often struggle to…

Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution,…

The problem of resource constrained scheduling in a dynamic and heterogeneous wireless setting is considered here. In our setup, the available limited bandwidth resources are allocated in order to serve randomly arriving service demands,…

$\textit{RigL}$, a sparse training algorithm, claims to directly train sparse networks that match or exceed the performance of existing dense-to-sparse training techniques (such as pruning) for a fixed parameter count and compute budget. We…

Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains…

Deep reinforcement learning(DRL) has shown significant promise in a wide range of applications including computer games and robotics. Yet, training DRL policies consume extraordinary computing resources resulting in dense policies which are…

Deep reinforcement learning (DRL) algorithms require substantial samples and computational resources to achieve higher performance, which restricts their practical application and poses challenges for further development. Given the…

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…

Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every timestep). Real Time…

Fully exploiting the learning capacity of neural networks requires overparameterized dense networks. On the other side, directly training sparse neural networks typically results in unsatisfactory performance. Lottery Ticket Hypothesis…

Reinforcement Learning (RL) is increasingly applied to large-scale decision-making problems like logistics, scheduling, and recommender systems, but existing algorithms struggle with the curse of dimensionality in such large discrete action…

The success of deep learning (DL) is often achieved with large models and high complexity during both training and post-training inferences, hindering training in resource-limited settings. To alleviate these issues, this paper introduces a…

With the rapid development of artificial intelligence, data-driven methods effectively overcome limitations in traditional portfolio optimization. Conventional models primarily employ long-only mechanisms, excluding highly correlated assets…

The autonomous control of flippers plays an important role in enhancing the intelligent operation of tracked robots within complex environments. While existing methods mainly rely on hand-crafted control models, in this paper, we introduce…

Deep reinforcement learning (DRL) is a machine learning-based method suited for complex and high-dimensional control problems. In this study, a real-time control system based on DRL is developed for long-term voltage stability events. The…

In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appropriate reward is difficult. Rewards obtained via actual…

Deep Reinforcement Learning (DRL) has emerged as a powerful model-free paradigm for learning optimal policies. However, in navigation tasks with cluttered environments, DRL methods often suffer from insufficient exploration, especially…

The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sparsifying DNNs before, during, and after training by pruning…