Tabular Q Learning

Tabular Q-learning is a reinforcement learning algorithm that aims to find optimal decision-making policies by iteratively updating a table representing the expected future reward for each state-action pair. Current research focuses on improving its efficiency and applicability, including optimizing its performance on specialized hardware, developing methods for effective state variable selection to reduce computational complexity, and adapting it for challenging environments like those with bimodal reward distributions. These advancements enhance the algorithm's practicality for real-world applications such as traffic control, assembly sequence planning, and even goal recognition, where its ability to learn from data and optimize for specific objectives is proving valuable.

Papers

May 7, 2024

SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems
Kailash Gogineni, Sai Santosh Dayapule, Juan Gómez-Luna, Karthikeya Gogineni, Peng Wei, Tian Lan, Mohammad Sadrosadati, Onur Mutlu, Guru Venkataramani
Reinforcement Learning System Description Reinforcement Learning Algorithm Efficient Reinforcement Learning Processing in Memory SWIFT DynGFN Tabular Q Learning

January 21, 2024

Information-Theoretic State Variable Selection for Reinforcement Learning
Charles Westphal, Stephen Hailes, Mirco Musolesi
Reinforcement Learning Proximal Policy Optimization Transfer Entropy Tabular Q Learning

October 19, 2023

Deep Reinforcement Learning-based Intelligent Traffic Signal Controls with Optimized CO2 emissions
Pedram Agand, Alexey Iskrov, Mo Chen
Transportation Network Adaptive Traffic Signal Control Signalized Intersection CO2 Emission Tabular Q Learning

July 3, 2023

Achieving Stable Training of Reinforcement Learning Agents in Bimodal Environments through Batch Learning
E. Hurwitz, N. Peace, G. Cevora
Reinforcement Learning Reinforcement Learning Agent Stochastic Environment Reinforcement Learning Problem Stable Training Batch Learning Multimodal Environment Tabular Q Learning

April 13, 2023

Deep reinforcement learning applied to an assembly sequence planning problem with user preferences
Miguel Neves, Pedro Neto
Deep Reinforcement Learning Q Learning Deep Q Learning User Preference Assembly Planning Tabular Q Learning Reinforcement Learning Performance

February 25, 2023

Reinforcement Learning based Autonomous Multi-Rotor Landing on Moving Platforms
Pascal Goldschmid, Aamir Ahmad
Reinforcement Learning Multi Rotor Autonomous Landing Moving Platform Tabular Q Learning

February 13, 2022

Goal Recognition as Reinforcement Learning
Leonardo Rosa Amado, Reuth Mirsky, Felipe Meneguzzi
Reinforcement Learning Online Inference Goal Recognition Tabular Q Learning

December 8, 2021

Convergence Results For Q-Learning With Experience Replay
Liran Szlak, Ohad Shamir
Q Learning Specific Heuristic Experience Replay Iteration Head Tabular Q Learning