相关论文: Contrastive Value Learning: Implicit Models for Si…

Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…

Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since…

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for…

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

Reinforcement learning (RL) is a powerful paradigm for learning to make sequences of decisions. However, RL has yet to be fully leveraged in robotics, principally due to its lack of scalability. Offline RL offers a promising avenue by…

Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of…

Preference-based reinforcement learning (PBRL) in the offline setting has succeeded greatly in industrial applications such as chatbots. A two-step learning framework where one applies a reinforcement learning step after a reward modeling…

In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems, where the aim is…

Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…

Offline reinforcement learning learns an effective policy on offline datasets without online interaction, and it attracts persistent research attention due to its potential of practical application. However, extrapolation error generated by…

Reinforcement learning (RL) is a technique to learn the control policy for an agent that interacts with a stochastic environment. In any given state, the agent takes some action, and the environment determines the probability distribution…

In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as length of…

Reinforcement learning (RL) in sparse-reward environments remains a significant challenge due to the lack of informative feedback. We propose a simple yet effective method that uses a small number of successful demonstrations to initialize…

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…

Transfer of recent advances in deep reinforcement learning to real-world applications is hindered by high data demands and thus low efficiency and scalability. Through independent improvements of components such as replay buffers or more…

Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically…

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider…

This paper proposes a novel deep reinforcement learning (RL) architecture, called Value Prediction Network (VPN), which integrates model-free and model-based RL methods into a single neural network. In contrast to typical model-based RL…

We introduce an offline reinforcement learning (RL) algorithm that explicitly clones a behavior policy to constrain value learning. In offline RL, it is often important to prevent a policy from selecting unobserved actions, since the…

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions. Poorly designed…