Related papers: Experience Sharing in Mutual Reinforcement Learnin…

We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies of isolated multi-agent on-policy optimization. HACRL…

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and…

Despite the rapid advancements of Large Language Models (LLMs), safety risks remain a critical challenge for low-resource languages. Existing safety datasets are predominantly English centric, limiting progress in multilingual safety…

As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized…

In this paper, we consider a transfer reinforcement learning problem involving agents with different action spaces. Specifically, for any new unseen task, the goal is to use a successful demonstration of this task by an expert agent in its…

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same…

The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability…

Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…

Large Language Models (LLMs) often suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist, limiting their diversity across a wide range of tasks. We introduce Group-Aware Policy…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

Group-based reinforcement learning methods, like Group Relative Policy Optimization (GRPO), are widely used nowadays to post-train large language models. Despite their empirical success, they exhibit structural mismatches between reward…

Meta-reinforcement learning (meta-RL) aims to quickly solve new tasks by leveraging knowledge from prior tasks. However, previous studies often assume a single mode homogeneous task distribution, ignoring possible structured heterogeneity…

Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with verifiable ground truths. Extending GRPO to open-domain…

Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing representations plays a fundamental role in capturing both unique…

As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term…

Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning.…

We investigate a paradigm in multi-task reinforcement learning (MT-RL) in which an agent is placed in an environment and needs to learn to perform a series of tasks, within this space. Since the environment does not change, there is…

Meta reinforcement learning (meta-RL) aims to learn a policy solving a set of training tasks simultaneously and quickly adapting to new tasks. It requires massive amounts of data drawn from training tasks to infer the common structure…

Reinforcement learning (RL) with diverse offline datasets can have the advantage of leveraging the relation of multiple tasks and the common skills learned across those tasks, hence allowing us to deal with real-world complex problems…