Reinforcement Learning

Reinforcement learning (RL) focuses on training agents to make optimal decisions in an environment by learning through trial and error, aiming to maximize cumulative rewards. Current research emphasizes improving RL's efficiency and robustness, particularly in areas like human-in-the-loop training (e.g., using human feedback to refine models), handling uncertainty and sparse rewards, and scaling to complex tasks (e.g., robotics, autonomous driving). Prominent approaches involve various policy gradient methods, Monte Carlo Tree Search, and the integration of large language models for improved decision-making and task decomposition. These advancements are driving progress in diverse fields, including robotics, game playing, and the development of more human-aligned AI systems.

Papers

October 7, 2024

October 6, 2024

October 5, 2024

On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning
Anas Barakat, Souradip Chakraborty, Peihong Yu, Pratap Tokekar, Amrit Singh Bedi
Reinforcement Learning Sample Complexity Action Space Policy OpTimization Policy Gradient Algorithm Utility Learning

October 4, 2024

Reinforcement Learning

Papers

SePPO: Semi-Policy Preference Optimization for Diffusion Alignment

LLMs Are In-Context Reinforcement Learners

Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

AlphaRouter: Quantum Circuit Routing with Reinforcement Learning and Tree Search

Reinforcement Learning Control for Autonomous Hydraulic Material Handling Machines with Underactuated Tools

Towards using Reinforcement Learning for Scaling and Data Replication in Cloud Systems

Mastering Chinese Chess AI (Xiangqi) Without Search

Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning

Towards Measuring Goal-Directedness in AI Systems

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications

GreenLight-Gym: A Reinforcement Learning Benchmark Environment for Greenhouse Crop Production Control

AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning

ShieldDiff: Suppressing Sexual Content Generation from Diffusion Models through Reinforcement Learning

Learning Humanoid Locomotion over Challenging Terrain

Training on more Reachable Tasks for Generalisation in Reinforcement Learning

GAP-RL: Grasps As Points for RL Towards Dynamic Object Grasping

Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization

SELU: Self-Learning Embodied MLLMs in Unknown Environments