Related papers: Unleashing Efficient Asynchronous RL Post-Training…
Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where long trajectories are generated token by token. We identify…
Training neural network often uses a machine learning framework such as TensorFlow and Caffe2. These frameworks employ a dataflow model where the NN training is modeled as a directed graph composed of a set of nodes. Operations in neural…
Reinforcement Learning from Human Feedback (RLHF) has been widely applied to Large Language Model (LLM) post-training to align model outputs with human preferences. Recent models, such as DeepSeek-R1, have also shown RLHF's potential to…
Real-time dynamic scheduling is a crucial but notoriously challenging task in modern manufacturing processes due to its high decision complexity. Recently, reinforcement learning (RL) has been gaining attention as an impactful technique to…
Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…
The goal of Continual Learning (CL) task is to continuously learn multiple new tasks sequentially while achieving a balance between the plasticity and stability of new and old knowledge. This paper analyzes that this insufficiency arises…
Reinforcement learning (RL) has demonstrated the ability to maintain the plasticity of the policy throughout short-term training in aerial robot control. However, these policies have been shown to loss of plasticity when extended to…
Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and training stages with fundamentally different resource…
Imitation learning has emerged as an effective approach for bootstrapping sequential decision-making in robotics, achieving strong performance even in high-dimensional dexterous manipulation tasks. Recent behavior cloning methods further…
We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily focus on regularizing model updates to preserve old…
Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call trajectory locking:…
Deep reinforcement learning (RL) has made groundbreaking advancements in robotics, data center management and other applications. Unfortunately, system-level bottlenecks in RL workloads are poorly understood; we observe fundamental…
We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability…
In the last decade, Reinforcement Learning (RL) has achieved remarkable success in the control and decision-making of complex dynamical systems. However, most RL algorithms rely on the Markov Decision Process assumption, which is violated…
Continual learning in robotics seeks systems that can constantly adapt to changing environments and tasks, mirroring human adaptability. A key challenge is refining dynamics models, essential for planning and control, while addressing…
Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…
The wall cycle in wall-bounded turbulent flows is a complex turbulence regeneration mechanism that remains not fully understood. This study explores the potential of deep reinforcement learning (DRL) for managing the wall regeneration cycle…
Robust Reinforcement Learning (RL) focuses on improving performances under model errors or adversarial attacks, which facilitates the real-life deployment of RL agents. Robust Adversarial Reinforcement Learning (RARL) is one of the most…
Reinforcement learning (RL) trains many agents, which is resource-intensive and must scale to large GPU clusters. Different RL training algorithms offer different opportunities for distributing and parallelising the computation. Yet,…
Synchronous federated learning (FL) scales poorly with the number of clients due to the straggler effect. Algorithms like FedAsync and GeneralizedFedAsync address this limitation by enabling asynchronous communication between clients and…