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

November 30, 2024

BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings
Karine Karine, Susan A. Murphy, Benjamin M. Marlin
Reinforcement Learning Thompson Sampling Severity Prediction Temporal Segmentation Batch Bayesian Optimization
PlanCritic: Formal Planning with Human Feedback
Owen Burns, Dana Hughes, Katia Sycara
Reinforcement Learning Task Planning Human Feedback High Level Plan Real World Planning

November 29, 2024

CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives
Armin Saghafian, Amirmohammad Izadi, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah
Reinforcement Learning CaRE SD Cross Modal Representation Learning Auxiliary Objective Multimodal Reinforcement Learning
HVAC-DPT: A Decision Pretrained Transformer for HVAC Control
Anaïs Berkes
Reinforcement Learning Decision Transformer Public Policy Heating, Ventilation, and Air Conditioning
Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning
Severin Bochem, Eduardo Gonzalez-Sanchez, Yves Bicker, Gabriele Fadini
Reinforcement Learning Strong Generalization Locomotion Policy Sim to Real Transfer Differentiable Simulator Real to Sim Sharpness Aware Optimization Sharpness Aware Training
Solving Rubik's Cube Without Tricky Sampling
Yicheng Lin, Siyu Liang
Reinforcement Learning Policy Gradient Sparse Reward Face Connected Cube
Training Agents with Weakly Supervised Feedback from Large Language Models
Dihong Gong, Pu Lu, Zelong Wang, Meng Zhou, Xiuqiang He
Reinforcement Learning Full Model Weakly Supervised Large Language LLM Based Agent Expert Trajectory Training Agent Iterative Interaction
o1-Coder: an o1 Replication for Coding
Yuxiang Zhang, Shangxi Wu, Yuqi Yang, Jiangming Shu, Jinlin Xiao, Chao Kong, Jitao Sang
Reinforcement Learning Monte Carlo Tree Search Programming Assistance Serial Reproduction System Approach
SANGO: Socially Aware Navigation through Grouped Obstacles
Rahath Malladi, Amol Harsh, Arshia Sangwan, Sunita Chauhan, Sandeep Manjanna
Reinforcement Learning Path Planning Robot Navigation Social Navigation Context Aware Navigation Obstacle Scenario
Proto Successor Measure: Representing the Space of All Possible Solutions of Reinforcement Learning
Siddhant Agarwal, Harshit Sikchi, Peter Stone, Amy Zhang
Reinforcement Learning Zero Shot Optimal Policy Solution Path Zero Shot Learning Deep Space Successor Representation

November 28, 2024

GRAPE: Generalizing Robot Policy via Preference Alignment
Zijian Zhang, Kaiyuan Zheng, Zhaorun Chen, Joel Jang, Yi Li, Chaoqi Wang, Mingyu Ding, Dieter Fox, Huaxiu Yao
Reinforcement Learning Manipulation Task Preference Alignment Vision Language Action Table Grape
Supervised Learning-enhanced Multi-Group Actor Critic for Live-stream Recommendation
Jingxin Liu, Xiang Gao, Yisha Li, Xin Li, Haiyang Lu, Ben Wang
Reinforcement Learning Recommender System Effective Recommendation Actor Critic Algorithm Multi Agent Actor Critic Live Video Injection Based Training Asymmetric Actor Critic
Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges
Majid Ghasemi, Amir Hossein Mousavi, Dariush Ebrahimi
Reinforcement Learning Artificial Intelligence Deep Reinforcement Learning Practical Algorithm Real World Comprehensive Survey Optimal Behavior

November 27, 2024

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
Letian Chen, Matthew Gombolay
Reinforcement Learning Full Model Robotics Domain Inverse Reinforcement Learning Policy Learning Noisy Demonstration Robot Behavior Interactive No Code Interactive Learning Reward Design
Dynamic Retail Pricing via Q-Learning -- A Reinforcement Learning Framework for Enhanced Revenue Management
Mohit Apte, Ketan Kale, Pranav Datar, Pratiksha Deshmukh
Reinforcement Learning New Framework Q Learning Dynamic Pricing Pricing Strategy Revenue Management
RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors
Anmol Dwivedi, Ali Tajer, Santiago Paternain, Nurali Virani
Reinforcement Learning Environment Exploration Power Grid Human Like RL Cascading Failure Blackout Mitigation
Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning
Neel Jawale, Byron Boots, Balakumar Sundaralingam, Mohak Bhardwaj
Reinforcement Learning Model Predictive Control Service Robot Non Prehensile Manipulation Batch Reinforcement Learning

November 26, 2024

Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Games with Delayed Rewards
Ahmad Ahmad, Mehdi Kermanshah, Kevin Leahy, Zachary Serlin, Ho Chit Siu, Makai Mann, Cristian-Ioan Vasile, Roberto Tron, Calin Belta
Reinforcement Learning Policy Gradient Optimal Policy Proximal Policy Optimization Reward Report Trust Region Policy Optimization Task Prediction Game Solving
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
Teng Wang, Wing-Yin Yu, Zhenqi He, Zehua Liu, Xiongwei Han, Hailei Gong, Han Wu, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong
Reinforcement Learning Search Query Open Source Thought Reasoning Level Mathematics Mathematical Model
Joint Combinatorial Node Selection and Resource Allocations in the Lightning Network using Attention-based Reinforcement Learning
Mahdi Salahshour, Amirahmad Shafiee, Mojtaba Tefagh
Reinforcement Learning Resource Allocation Revenue Maximization Joint Selection Payment Channel

Reinforcement Learning

Papers

BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings

PlanCritic: Formal Planning with Human Feedback

CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives

HVAC-DPT: A Decision Pretrained Transformer for HVAC Control

Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning

Solving Rubik's Cube Without Tricky Sampling

Training Agents with Weakly Supervised Feedback from Large Language Models

o1-Coder: an o1 Replication for Coding

SANGO: Socially Aware Navigation through Grouped Obstacles

Proto Successor Measure: Representing the Space of All Possible Solutions of Reinforcement Learning

GRAPE: Generalizing Robot Policy via Preference Alignment

Supervised Learning-enhanced Multi-Group Actor Critic for Live-stream Recommendation

Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics

Dynamic Retail Pricing via Q-Learning -- A Reinforcement Learning Framework for Enhanced Revenue Management

RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors

Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning

Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Games with Delayed Rewards

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving

Joint Combinatorial Node Selection and Resource Allocations in the Lightning Network using Attention-based Reinforcement Learning