paper-with-me

홈 › Papers

Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraints

2022-11-27 · Hengquan Guo, Qi Zhu, Xin Liu

This paper studies the problem of stochastic continuum-armed bandit with constraints (SCBwC), where we optimize a black-box reward function $f(x)$ subject to a black-box constraint function $g(x)\leq 0$ over a continuous space $\mathcal X$. We model reward and constraint functions via Gaussian processes (GPs) and propose a Rectified Pessimistic-Optimistic Learning framework (RPOL), a penalty-based method incorporating optimistic and pessimistic GP bandit learning for reward and constraint functions, respectively. We consider the metric of cumulative constraint violation $\sum_{t=1}^T(g(x_t))^{+},$ which is strictly stronger than the traditional long-term constraint violation $\sum_{t=1}^Tg(x_t).$ The rectified design for the penalty update and the pessimistic learning for the constraint function in RPOL guarantee the cumulative constraint violation is minimal. RPOL can achieve sublinear regret and cumulative constraint violation for SCBwC and its variants (e.g., under delayed feedback and non-stationary environment). These theoretical results match their unconstrained counterparts. Our experiments justify RPOL outperforms several existing baseline algorithms.

📄 PDF Abstract BibTeX arXiv:2211.14720

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes

Similar Papers 제목 키워드 기반

On the Optimality of Batch Policy Optimization Algorithms

2021-04-06 · Chenjun Xiao, Yifan Wu, Tor Lattimore, Bo Dai 외

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foun…

Value prediction

On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit

2025-01-01 · Xiaoyi Wu, Bo Ji, Bin Li

Combinatorial Multi-Armed Bandit with fairness constraints is a framework where multiple arms form a super arm and can be pulled in each round under uncertainty to maximize cumulative rewards while ensuring the minimum a…

Fairness

Stochastic Bandits with Linear Constraints

2020-06-17 · Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett, Heinrich Jiang

We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies, whose expected cumulative reward over the course of $T$ rounds is maximum, and each has an expect…

Multi-Armed Bandits

Ensuring Safety in an Uncertain Environment: Constrained MDPs via Stochastic Thresholds

2025-04-07 · Qian Zuo, Fengxiang He

This paper studies constrained Markov decision processes (CMDPs) with constraints against stochastic thresholds, aiming at the safety of reinforcement learning in unknown and uncertain environments. We leverage a Growing…

reinforcement-learningReinforcement Learning

Optimistic Exploration even with a Pessimistic Initialisation

2020-02-26 · ICLR 2020 1 · Tabish Rashid, Bei Peng, Wendelin Böhmer, Shimon Whiteson

Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely on it. However, model-free deep RL algor…

Efficient ExplorationQ-LearningReinforcement LearningReinforcement Learning (RL)