8 papers
Rate-Optimal Algorithm for Adversarial Linear CMDPs
Kihyun Yu, Honghao Wei, Dabeen Lee
We study episodic adversarial linear constrained Markov decision processes (CMDPs) with unknown transitions, where both the loss and constraint functions may vary adversarially acr…
Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation
Kihyun Yu, Seoungbin Bae, Dabeen Lee
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this sett…
Constrained Online Convex Optimization without Slater's Condition
Kihyun Yu, Junehee Lee, Dabeen Lee
We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints. For stochastic constraints, existing algorithms that achieve near…
Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
Kihyun Yu, Beomhan Baek, Dabeen Lee
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Our contributions are twofold. First, we establish…
Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses
Kihyun Yu, Seoungbin Bae, Dabeen Lee
Existing work on linear constrained Markov decision processes (CMDPs) has primarily focused on stochastic settings, where the losses and costs are either fixed or drawn from fixed…
Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards
Kihyun Yu, Seoungbin Bae, Dabeen Lee
We study safe reinforcement learning in finite-horizon linear mixture constrained Markov decision processes (CMDPs) with adversarial rewards under full-information feedback and an…
An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints
Jiahui Zhu, Kihyun Yu, Dabeen Lee +2
Online safe reinforcement learning (RL) plays a key role in dynamic environments, with applications in autonomous driving, robotics, and cybersecurity. The objective is to learn op…
Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism
Kihyun Yu, Duksang Lee, William Overman +1
This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel an…