相关论文: AMPED: Adaptive Multi-objective Projection for bal…

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

Multi-task learning (MTL) is a subfield of machine learning with important applications, but the multi-objective nature of optimization in MTL leads to difficulties in balancing training between tasks. The best MTL optimization methods…

Identifying statistical regularities in solutions to some tasks in multi-task reinforcement learning can accelerate the learning of new tasks. Skill learning offers one way of identifying these regularities by decomposing pre-collected…

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment. While the capabilities of MBRL agents have significantly improved in recent…

The Centralized Training with Decentralized Execution (CTDE) paradigm is widely used in cooperative multi-agent reinforcement learning. However, conventional methods based on CTDE can suffer from value underestimation and converge to…

Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which is computationally expensive and yields overly conservative…

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…

Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at design time where related tasks could borrow representational…

Portfolio optimization in non-stationary markets is challenging due to regime shifts, dynamic correlations, and the limited interpretability of deep reinforcement learning (DRL) policies. We propose a Segmented Allocation with…

An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Recent advances in multimodal reward modeling have been largely driven by a paradigm shift from discriminative to generative approaches. Building on this progress, recent studies have further employed reinforcement learning from verifiable…

Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach…

Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several…

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…

Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively explored depth expansion, width expansion remains significantly understudied, with the few existing…

Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization. RL is also very brittle; agents often overfit to their training…

Researchers and practitioners are increasingly considering reinforcement learning to optimize decisions in complex domains like robotics and healthcare. To date, these efforts have largely utilized expectation-based learning. However,…

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent…

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging…