State Reward

State reward, a core component of reinforcement learning, defines the feedback an agent receives for its actions within a given state, guiding its learning process towards optimal behavior. Current research focuses on improving sample efficiency through techniques like reverse experience replay and unique experience selection in replay buffers, as well as enhancing reward design using methods such as barrier-based style rewards and potential-based rewards derived from formal specifications. These advancements aim to address challenges like data inefficiency and reward sparsity, ultimately leading to more robust and efficient reinforcement learning algorithms applicable to diverse domains, including robotics and education.

Papers

September 24, 2024

A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards
Gijeong Kim, Yong-Hoon Lee, Hae-Won Park
Reward Model Quadrupedal Robot Legged Locomotion Learning Framework Legged Robot Locomotion State Reward

August 30, 2024

A Tighter Convergence Proof of Reverse Experience Replay
Nan Jiang, Jinzhao Li, Yexiang Xue
Reinforcement Learning Learning Rate Experience Replay State Reward

June 25, 2024

The State-Action-Reward-State-Action Algorithm in Spatial Prisoner's Dilemma Game
Lanyu Yang, Dongchun Jiang, Fuqiang Guo, Mingjian Fu
Reinforcement Learning Imitation Learning Cooperative Behavior Evolutionary Game Theory Dilemma Game State Reward

February 5, 2024

Frugal Actor-Critic: Sample Efficient Off-Policy Deep Reinforcement Learning Using Unique Experiences
Nikhil Kumar Singh, Indranil Saha
Actor Critic Reinforcement Learning Policy Actor Critic Model Free Policy State Reward

January 19, 2024

Episodic Reinforcement Learning with Expanded State-reward Space
Dayang Liang, Yaru Zhang, Yunlong Liu
Deep Reinforcement Learning Episodic Memory Episodic Reinforcement Learning Model Free Deep Reinforcement Learning Prompt Expansion State Reward Episodic Control

May 24, 2023

Provable Offline Preference-Based Reinforcement Learning
Wenhao Zhan, Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun
Reinforcement Learning Offline Data Implicit Reward State Reward Offline Preference Based Reinforcement Learning Single Policy Concentrability

November 1, 2022

Reinforcement Learning in Education: A Multi-Armed Bandit Approach
Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman
Reinforcement Learning Online Learning Education Domain Agent Based Model Reinforcement Learning Research Recommendation Problem State Reward

August 26, 2022

Visual processing in context of reinforcement learning
Hlynur Davíð Hlynsson
Reinforcement Learning Deep Reinforcement Learning Context Information State Representation Visual Processing State Reward

June 1, 2022

Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble
Fan-Ming Luo, Xingchen Cao, Rong-Jun Qin, Yang Yu
Reward Function Inverse Reinforcement Learning State Reward

April 27, 2022

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair, Patrick Yin, Sergey Levine
Reinforcement Learning Goal Conditioned Reinforcement Learning Bisimulation Metric State Reward Creative Analogy Goal Conditioned Agent

February 4, 2022

Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives
Anand Balakrishnan, Stefan Jakšić, Edgar A. Aguilar, Dejan Ničković, Jyotirmoy V. Deshmukh
Reinforcement Learning Model Free Reinforcement Learning Symbolic Expression State Reward Markovian Reward

December 1, 2021

Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes
Qin Lu, Georgios B. Giannakis
Reinforcement Learning Gaussian Process Robust Version Diverse Ensemble Value Function Temporal Difference Learning Trajectory Wise Reward State Reward