Policy Gradient Methods

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 151–175 of 382 papers

Title	Date	Tasks	Status	Hype
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function	May 25, 2022	Policy Gradient MethodsReinforcement Learning (RL)	—Unverified	0
The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure	May 20, 2022	Efficient ExplorationPolicy Gradient Methods	CodeCode Available	1
Momentum-Based Policy Gradient with Second-Order Information	May 17, 2022	Policy Gradient Methods	—Unverified	0
Stochastic first-order methods for average-reward Markov decision processes	May 11, 2022	Policy Gradient Methods	—Unverified	0
Learning to Constrain Policy Optimization with Virtual Trust Region	Apr 20, 2022	Atari GamesPolicy Gradient Methods	—Unverified	0
Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization	Apr 12, 2022	Autonomous VehiclesPolicy Gradient Methods	—Unverified	0
Synthesis of Stabilizing Recurrent Equilibrium Network Controllers	Mar 31, 2022	Policy Gradient Methods	CodeCode Available	0
Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach	Mar 29, 2022	Hierarchical Reinforcement LearningMulti-agent Reinforcement Learning	—Unverified	0
Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment	Mar 24, 2022	Policy Gradient Methods	—Unverified	0
Linear convergence of a policy gradient method for some finite horizon continuous time control problems	Mar 22, 2022	Policy Gradient Methodsreinforcement-learning	—Unverified	0
Policy Learning and Evaluation with Randomized Quasi-Monte Carlo	Feb 16, 2022	continuous-controlContinuous Control	—Unverified	0
Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence	Feb 8, 2022	Multi-agent Reinforcement LearningPolicy Gradient Methods	—Unverified	0
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation	Feb 1, 2022	Policy Gradient Methods	—Unverified	0
Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods	Jan 28, 2022	Knowledge GraphsPolicy Gradient Methods	CodeCode Available	0
Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity	Jan 24, 2022	Policy Gradient Methods	—Unverified	0
Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning	Jan 22, 2022	Policy Gradient Methodsreinforcement-learning	CodeCode Available	0
On the Convergence Rates of Policy Gradient Methods	Jan 19, 2022	Policy Gradient Methods	—Unverified	0
Reinforcement Learning based Sequential Batch-sampling for Bayesian Optimal Experimental Design	Dec 21, 2021	Deep Reinforcement LearningExperimental Design	—Unverified	0
MDPGT: Momentum-based Decentralized Policy Gradient Tracking	Dec 6, 2021	Multi-agent Reinforcement LearningPolicy Gradient Methods	CodeCode Available	0
Episodic Policy Gradient Training	Dec 3, 2021	Policy Gradient MethodsScheduling	CodeCode Available	1
Global Convergence Using Policy Gradient Methods for Model-free Markovian Jump Linear Quadratic Control	Nov 30, 2021	Policy Gradient Methods	—Unverified	0
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods	Nov 6, 2021	MuJoCoPolicy Gradient Methods	CodeCode Available	0
Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch	Nov 4, 2021	Policy Gradient Methods	—Unverified	0
Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution	Nov 3, 2021	continuous-controlContinuous Control	—Unverified	0
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings	Oct 30, 2021	Policy Gradient Methodsreinforcement-learning	—Unverified	0

Show:10 25 50

← PrevPage 7 of 16Next →

No leaderboard results yet.