Related papers: Learn a Prior for RHEA for Better Online Planning
Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics.…
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack…
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,…
Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon planning, and settings with sparse rewards. However, learning…
Large language models (LLMs) are increasingly adopted as the backbone of recommender systems. However, user-item interactions in real-world scenarios are non-stationary, making preference drift over time inevitable. Existing model update…
Hindsight Experience Replay (HER) is a technique used in reinforcement learning (RL) that has proven to be very efficient for training off-policy RL-based agents to solve goal-based robotic manipulation tasks using sparse rewards. Even…
With the rapid growth of user historical behavior data, user interest modeling has become a prominent aspect in Click-Through Rate (CTR) prediction, focusing on learning user intent representations. However, this complexity poses…
Hierarchical Reinforcement Learning (HRL) approaches have shown successful results in solving a large variety of complex, structured, long-horizon problems. Nevertheless, a full theoretical understanding of this empirical evidence is…
Manipulation in clutter requires solving complex sequential decision making problems in an environment rich with physical interactions. The transfer of motion planning solutions from simulation to the real world, in open-loop, suffers from…
In this paper, a new swarm intelligence algorithm based on orca behaviors is proposed for problem solving. The algorithm called artificial orca algorithm (AOA) consists of simulating the orca lifestyle and in particular the social…
A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…
In robust optimization problems, the magnitude of perturbations is relatively small. Consequently, solutions within certain regions are less likely to represent the robust optima when perturbations are introduced. Hence, a more efficient…
We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction. The framework mitigates the challenges that arise…
Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and…
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…
We provide a general mechanism to design online learning algorithms based on a minimax analysis within a drifting-games framework. Different online learning settings (Hedge, multi-armed bandit problems and online convex optimization) are…
Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a…
This paper studies an online optimization problem with a finite prediction window of cost functions and additional switching costs on decisions. We propose two gradient-based online algorithms: Receding Horizon Gradient Descent (RHGD), and…
After the repeal of Roe vs. Wade in June 2022, women face long-distance travel across state lines to access abortion care. For women who also face socioeconomic hardship, travel for abortion care is a significant burden. To ease this…
Metaheuristics (MHs) in general and Evolutionary Algorithms (EAs) in particular are well known tools for successful optimization of difficult problems. But when is their application meaningful and how does one approach such a project as a…