相关论文: Contextual Bilevel Reinforcement Learning for Ince…

Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov…

In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requirements in secondary cumulative reward constraints. Several…

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But…

Model-based reinforcement learning (MBRL) has recently gained immense interest due to its potential for sample efficiency and ability to incorporate off-policy data. However, designing stable and efficient MBRL algorithms using rich…

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…

Hierarchical Reinforcement Learning (HRL) enhances the scalability of decision-making in long-horizon tasks by introducing temporal abstraction through options-policies that span multiple timesteps. Despite its theoretical appeal, the…

Bilevel reinforcement learning (RL), which features intertwined two-level problems, has attracted growing interest recently. The inherent non-convexity of the lower-level RL problem is, however, to be an impediment to developing bilevel…

Autocurricular training is an important sub-area of multi-agent reinforcement learning~(MARL) that allows multiple agents to learn emergent skills in an unsupervised co-evolving scheme. The robotics community has experimented autocurricular…

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

Policy-based algorithms are among the most widely adopted techniques in model-free RL, thanks to their strong theoretical groundings and good properties in continuous action spaces. Unfortunately, these methods require precise and…

Batch reinforcement learning (RL) defines the task of learning from a fixed batch of data lacking exhaustive exploration. Worst-case optimality algorithms, which calibrate a value-function model class from logged experience and perform some…

In a Stackelberg congestion game (SCG), a leader aims to maximize their own gain by anticipating and manipulating the equilibrium state at which the followers settle by playing a congestion game. Often formulated as bilevel programs,…

We study reinforcement learning by combining recent advances in regularized linear programming formulations with the classical theory of stochastic approximation. Motivated by the challenge of designing algorithms that leverage off-policy…

We propose a novel hierarchical reinforcement learning framework for quadruped locomotion over challenging terrain. Our approach incorporates a two-layer hierarchy in which a high-level policy (HLP) selects optimal goals for a low-level…

Real-world decision-making problems are often marked by complex, uncertain dynamics that can shift or break under changing conditions. Traditional Model-Based Reinforcement Learning (MBRL) approaches learn predictive models of environment…

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c)…

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…

Hierarchical reinforcement learning (HRL) proposes to solve difficult tasks by performing decision-making and control at successively higher levels of temporal abstraction. However, off-policy HRL often suffers from the problem of a…

Constrained Reinforcement Learning (CRL) tackles sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints, which are often formulated as…