Search Results for author:
Found 15 papers, 2 papers with code
Exploration Through Bias: Revisiting Biased Maximum Likelihood Estimation in Stochastic Multi-Armed Bandits
We propose a new family of bandit algorithms, that are formulated in a general way based on the Biased Maximum Likelihood Estimation (BMLE) method originally appearing in the adaptive control literature.
Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees
In this paper, we rethink off-policy learning via Coordinate Ascent Policy Optimization (CAPO), an off-policy actor-critic algorithm that decouples policy improvement from the state distribution of the behavior policy without using the policy gradient.
Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
Many real-world continuous control problems are in the dilemma of weighing the pros and cons, multi-objective reinforcement learning (MORL) serves as a generic framework of learning control policies for different preferences over objectives.
Neural Frank-Wolfe Policy Optimization for Region-of-Interest Intra-Frame Coding with HEVC/H.265
Recently, the dual-critic design is proposed to update the actor by alternating the rate and distortion critics.
Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits
Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs.
Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective
Policy optimization is a fundamental principle for designing reinforcement learning algorithms, and one example is the proximal policy optimization algorithm with a clipped surrogate objective (PPO-Clip), which has been popularly used in deep reinforcement learning due to its simplicity and effectiveness.
NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL
This paper proposes NeurWIN, a neural Whittle index network that seeks to learn the Whittle indices for any restless bandits by leveraging mathematical properties of the Whittle indices.
Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization
While it serves as a natural idea to combine DQN and an existing few-shot learning method, we identify that such a direct combination does not perform well due to severe overfitting, which is particularly critical in BO due to the need of a versatile sampling policy.
Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization
Action-constrained reinforcement learning (RL) is a widely-used approach in various real-world applications, such as scheduling in networked systems with resource constraints and control of a robot with kinematic constraints.
Rethinking Deep Policy Gradients via State-Wise Policy Improvement
Deep policy gradient is one of the major frameworks in reinforcement learning, and it has been shown to improve parameterized policies across various tasks and environments.
Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits
Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems.
Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning
With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue.
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
To choose the bias-growth rate $\alpha(t)$ in RBMLE, we reveal the nontrivial interplay between $\alpha(t)$ and the regret bound that generally applies in both the Exponential Family as well as the sub-Gaussian/Exponential family bandits.
Streaming Network Embedding through Local Actions
Thus the approach of adapting the existing methods to the streaming environment faces non-trivial technical challenges.
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging
Sequential decision making for lifetime maximization is a critical problem in many real-world applications, such as medical treatment and portfolio selection.
