Related papers: Bootstrapping Task Spaces for Self-Improvement

In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an…

This paper addresses the problem of designing control policies for agents with unknown stochastic dynamics and control objectives specified using Linear Temporal Logic (LTL). Recent Deep Reinforcement Learning (DRL) algorithms have aimed to…

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in…

Deep Reinforcement Learning (DRL) is widely used in task-oriented dialogue systems to optimize dialogue policy, but it struggles to balance exploration and exploitation due to the high dimensionality of state and action spaces. This…

Efficiently tackling multiple tasks within complex environment, such as those found in robot manipulation, remains an ongoing challenge in robotics and an opportunity for data-driven solutions, such as reinforcement learning (RL).…

We consider the problem of reward learning for temporally extended tasks. For reward learning, inverse reinforcement learning (IRL) is a widely used paradigm. Given a Markov decision process (MDP) and a set of demonstrations for a task, IRL…

In-context learning (ICL), a predominant trend in instruction learning, aims at enhancing the performance of large language models by providing clear task guidance and examples, improving their capability in task understanding and…

Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is therefore heteroscedastic. Classical exploration strategies…

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agentic paradigm. However,…

Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and…

Self-reflection for Large Language Models (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs' internal reflection ability or external feedback. However,…

Scaling up the deployment of autonomous excavators is of great economic and societal importance. Yet it remains a challenging problem, as effective systems must robustly handle unseen worksite conditions and new hardware configurations.…

Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance,…

A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more computation or interaction is available. Even the…

Deep reinforcement learning has enabled human-level or even super-human performance in various types of games. However, the amount of exploration required for learning is often quite large. Deep reinforcement learning also has super-human…

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…

Reinforcement learning (RL) systems have countless applications, from energy-grid management to protein design. However, such real-world scenarios are often extremely difficult, combinatorial in nature, and require complex coordination…

Reinforcement learning (RL) is one of the three basic paradigms of machine learning. It has demonstrated impressive performance in many complex tasks like Go and StarCraft, which is increasingly involved in smart manufacturing and…

We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language -- linear temporal logic (LTL) -- and can specify a…