相关论文: Hindsight Expectation Maximization for Goal-condit…

Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as epsilon-greedy. There are…

The endeavor of artificial intelligence (AI) is to design autonomous agents capable of achieving complex tasks. Namely, reinforcement learning (RL) proposes a theoretical background to learn optimal behaviors. In practice, RL algorithms…

Hierarchical Reinforcement Learning (HRL) is a promising approach to solving long-horizon problems with sparse and delayed rewards. Many existing HRL algorithms either use pre-trained low-level skills that are unadaptable, or require…

Deep reinforcement Learning for end-to-end driving is limited by the need of complex reward engineering. Sparse rewards can circumvent this challenge but suffers from long training time and leads to sub-optimal policy. In this work, we…

To avoid myopic behavior, multi-step lookahead Bayesian optimization (BO) algorithms consider the sequential nature of BO and have demonstrated promising results in recent years. However, owing to the curse of dimensionality, most of these…

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the…

Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…

Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper…

Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…

Common approaches to Reinforcement Learning (RL) are seriously challenged by large-scale applications involving huge state spaces and sparse delayed reward feedback. Hierarchical Reinforcement Learning (HRL) methods attempt to address this…

The expectation--maximization (EM) algorithm combines global monotonicity, local linear convergence, and strong practical robustness, but these features are usually analyzed separately. Global descent is nonlinear, whereas local convergence…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the…

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However,…

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

As machine learning has moved towards leveraging large models as priors for downstream tasks, the community has debated the right form of prior for solving reinforcement learning (RL) problems. If one were to try to prefetch as much…

Solving goal-oriented tasks is an important but challenging problem in reinforcement learning (RL). For such tasks, the rewards are often sparse, making it difficult to learn a policy effectively. To tackle this difficulty, we propose a new…

Goal-conditioned hierarchical reinforcement learning (HRL) has shown promising results for solving complex and long-horizon RL tasks. However, the action space of high-level policy in the goal-conditioned HRL is often large, so it results…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

The $\ell_0$-constrained empirical risk minimization ($\ell_0$-ERM) is a promising tool for high-dimensional statistical estimation. The existing analysis of $\ell_0$-ERM estimator is mostly on parameter estimation and support recovery…