相关论文: Upside-Down Reinforcement Learning Can Diverge in …

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous…

In this paper, we propose and study opportunistic reinforcement learning - a new variant of reinforcement learning problems where the regret of selecting a suboptimal action varies under an external environmental condition known as the…

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…

Empowered by deep neural networks, deep reinforcement learning (DRL) has demonstrated tremendous empirical successes in various domains, including games, health care, and autonomous driving. Despite these advancements, DRL is still…

Reinforcement learning is an emerging approaches to facilitate multi-stage sequential decision-making problems. This paper studies a real-time multi-stage stochastic power dispatch considering multivariate uncertainties. Current researches…

Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor…

Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on…

Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, an influential class of methods, mutual information skill…

Reinforcement Learning (RL) has demonstrated a great potential for automatically solving decision-making problems in complex uncertain environments. RL proposes a computational approach that allows learning through interaction in an…

One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The…

The high-dimensional or sparse reward task of a reinforcement learning (RL) environment requires a superior potential controller such as hierarchical reinforcement learning (HRL) rather than an atomic RL because it absorbs the complexity of…

A residual deep reinforcement learning (RDRL) approach is proposed by integrating DRL with model-based optimization for inverter-based volt-var control in active distribution networks when the accurate power flow model is unknown. RDRL…

Episodic training, where an agent's environment is reset after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents. The underlying assumption that the environment can be easily reset…

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the…

Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks. We are motivated to study how we can take full advantage of supervised loss functions for stably training deep reinforcement…

When applying offline reinforcement learning (RL) in healthcare scenarios, the out-of-distribution (OOD) issues pose significant risks, as inappropriate generalization beyond clinical expertise can result in potentially harmful…

Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such optimization methods…

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Deep Reinforcement Learning (DRL) algorithms have achieved great success in solving many challenging tasks while their black-box nature hinders interpretability and real-world applicability, making it difficult for human experts to…

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…