Related papers: PretrainZero: Reinforcement Active Pretraining
Recently, deep reasoning LLMs (e.g., OpenAI o1 and DeepSeek-R1) have shown promising performance in various downstream tasks. Free translation is an important and interesting task in the multilingual world, which requires going beyond…
Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive…
Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking…
Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in large reasoning models. To analyze reasoning dynamics, we use synthetic logic puzzles as training data due to their controllable…
Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train…
Enhancing the complex reasoning capabilities of Large Language Models (LLMs) attracts widespread attention. While reinforcement learning (RL) has shown superior performance for improving complex reasoning, its impact on cross-lingual…
Enhancing the reasoning capabilities of large language models (LLMs) typically relies on massive computational resources and extensive datasets, limiting accessibility for resource-constrained settings. Our study investigates the potential…
Everything else being equal, simpler models should be preferred over more complex ones. In reinforcement learning (RL), simplicity is typically quantified on an action-by-action basis -- but this timescale ignores temporal regularities,…
We introduce Reward-Zero, a general-purpose implicit reward mechanism that transforms natural-language task descriptions into dense, semantically grounded progress signals for reinforcement learning (RL). Reward-Zero serves as a simple yet…
Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains…
Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…
This paper addresses the problem of inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. IRL can provide a generalizable and compact representation for apprenticeship learning, and…
Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over…
Reinforcement Learning (RL) has been widely used in many applications, particularly in gaming, which serves as an excellent training ground for AI models. Google DeepMind has pioneered innovations in this field, employing reinforcement…
Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…
Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…
Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this…
Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…
Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets…
A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks…