Search Results for author:
Found 10 papers, 0 papers with code
Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
This paper explores the realm of infinite horizon average reward Constrained Markov Decision Processes (CMDP).
Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes
Remarkably, this paper marks a pioneering effort by presenting the first exploration into regret-bound computation for the general parameterized policy gradient algorithm in the context of average reward scenarios.
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm
We propose a novel Conservative Natural Policy Gradient Primal-Dual Algorithm (C-NPG-PD) to achieve zero constraint violation while achieving state of the art convergence results for the objective value function.
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach
To achieve that, we advocate the use of randomized primal-dual approach to solve the CMDP problems and propose a conservative stochastic primal-dual algorithm (CSPDA) which is shown to exhibit $\tilde{\mathcal{O}}\left(1/\epsilon^2\right)$ sample complexity to achieve $\epsilon$-optimal cumulative reward with zero constraint violations.
Concave Utility Reinforcement Learning with Zero-Constraint Violations
We consider the problem of tabular infinite horizon concave utility reinforcement learning (CURL) with convex constraints.
Markov Decision Processes with Long-Term Average Constraints
We consider the problem of constrained Markov Decision Process (CMDP) where an agent interacts with a unichain Markov Decision Process.
Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm
Many engineering problems have multiple objectives, and the overall aim is to optimize a non-linear function of these objectives.
Multi-Objective Reinforcement Learning
reinforcement-learning
Model-Free Algorithm and Regret Analysis for MDPs with Long-Term Constraints
This paper uses concepts from constrained optimization and Q-learning to propose an algorithm for CMDP with long-term constraints.
Provably Efficient Model-Free Algorithm for MDPs with Peak Constraints
The proposed algorithm is proved to achieve an $(\epsilon, p)$-PAC policy when the episode $K\geq\Omega(\frac{I^2H^6SA\ell}{\epsilon^2})$, where $S$ and $A$ are the number of states and actions, respectively.
Escaping Saddle Points for Zeroth-order Nonconvex Optimization using Estimated Gradient Descent
Gradient descent and its variants are widely used in machine learning.
