相关论文: Flattening Hierarchies with Policy Bootstrapping

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \textit{specify} and \textit{ground} these goals in such a…

We present Gradient Boosting Reinforcement Learning (GBRL), a framework that adapts the strengths of gradient boosting trees (GBT) to reinforcement learning (RL) tasks. While neural networks (NNs) have become the de facto choice for RL,…

Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algorithms. A recent work, called Goal-Conditioned Supervised…

Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially…

Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tasks involving sparse rewards. Existing goal-conditioned and…

Offline goal-conditioned reinforcement learning (GCRL) offers a practical learning paradigm in which goal-reaching policies are trained from abundant state-action trajectory datasets without additional environment interaction. However,…

Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets. This is a particularly difficult setup, especially when learning to achieve multiple different goals or outcomes under a given…

Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant…

Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can…

This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenarios, learning representations that align state and goal latents is a challenge that…

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms take the approach of constraining or regularizing…

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoals to a lower level has been shown to enable fast learning…

Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…

Goal-conditioned reinforcement learning (RL) can solve tasks in a wide range of domains, including navigation and manipulation, but learning to reach distant goals remains a central challenge to the field. Learning to reach such goals is…

Manipulating articulated tools, such as tweezers or scissors, has rarely been explored in previous research. Unlike rigid tools, articulated tools change their shape dynamically, creating unique challenges for dexterous robotic hands. In…

Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient due to bootstrapping. While recent work has explored contrastive and supervised…

Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by decomposing tasks, most existing methods rely on separate high- and low-level networks and…

Deep reinforcement learning algorithms have succeeded in several challenging domains. Classic Online RL job schedulers can learn efficient scheduling strategies but often takes thousands of timesteps to explore the environment and adapt…

We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in…

Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine learning. While self-supervised learning in other domains aims to find patterns in a fixed…