相关论文: Meta-RTL: Reinforcement-Based Meta-Transfer Learni…

Recent advancements in reinforcement learning (RL) for large language models (LLMs), exemplified by DeepSeek R1, have shown that even a simple question-answering task can substantially improve an LLM's reasoning capabilities. In this work,…

Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks.…

Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchmarks at smaller parameter budgets. However, attempts to further improve LoopLM reasoning with…

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks. The training tasks are usually hand-crafted to be representative of the expected distribution…

One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a…

We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of…

Meta-learning is a branch of machine learning which aims to quickly adapt models, such as neural networks, to perform new tasks by learning an underlying structure across related tasks. In essence, models are being trained to learn new…

Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering…

Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with…

Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving…

In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent…

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an…

Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional…

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience,…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning…