Arnob Ghosh
9 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
🏆
Keyword Champion
(4)
Top co-authors
Research topics
Reinforcement Learning
(9)
Machine Learning
(7)
Methods
(7)
Optimization & Theory
(6)
Applications
(4)
Artificial Intelligence
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Deep Learning
(1)
Mathematics & Optimization
(1)
Robotics
(1)
Capabilities
(1)
Learning Types · Deep Learning
(1)
Optimization
(1)
Keywords
regret bound
(7)
linear function approximation
(4)
model-free reinforcement learning
(4)
constrained markov decision process
(3)
reinforcement learning
(2)
policy optimization
(2)
primal-dual algorithm
(2)
multi-agent system
(2)
online convex optimization
(1)
primal-dual optimization
(1)
policy improvement
(1)
non-convex safe least squares value iteration (ncs-lsvi)
(1)
constrained reinforcement learning
(1)
safe reinforcement learning
(1)
regret
(1)
offline reinforcement learning
(1)
stackelberg equilibrium
(1)
linear mdp
(1)
average reward
(1)
adversarial learning
(1)
Papers
Online Learning in Risk Sensitive constrained MDP
ICML 2025
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
ICML 2025
Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
ICLR 2024
Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
NeurIPS 2024
Towards Achieving Sub-linear Regret and Hard Constraint Violation in Model-free RL
AISTATS 2024
Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation
ICLR 2023
Provably Efficient Model-Free Algorithms for Non-stationary CMDPs
AISTATS 2023
Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation
L4DC 2023
Provably Efficient Model-Free Constrained RL with Linear Function Approximation
NeurIPS 2022