Papers Policy Gradient Methods
“Policy Gradient Methods” 태그가 달린 논문 382편 · 필터 해제
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Reinforcement Learning in large action spaces is a challenging problem. Cooperative multi-agent reinforcement learning (MARL) exacerbates matters by imposing various constraints on communication and observability. In thi…
Learning TheoryMulti-agent Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2Meta Learning the Step Size in Policy Gradient Methods
Policy-based algorithms are among the most widely adopted techniques in model-free RL, thanks to their strong theoretical groundings and good properties in continuous action spaces. Unfortunately, these methods require p…
Meta-LearningMeta Reinforcement LearningPolicy Gradient MethodsControlling an Inverted Pendulum with Policy Gradient Methods-A Tutorial
This paper provides the details of implementing two important policy gradient methods to solve the inverted pendulum problem. These are namely the Deep Deterministic Policy Gradient (DDPG) and the Proximal Policy Optimiz…
OpenAI GymPolicy Gradient MethodsOn the Linear convergence of Natural Policy Gradient Algorithm
Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradi…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients
Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios. However, there is a significant perf…
Multi-agent Reinforcement LearningPolicy Gradient MethodsReinforcement Learning (RL)SMAC+2Model-free Policy Learning with Reward Gradients
Despite the increasing popularity of policy gradient methods, they are yet to be widely utilized in sample-scarce applications, such as robotics. The sample efficiency could be improved by making best usage of available …
Continuous ControlmodelMuJoCoPolicy Gradient MethodsSoftmax Policy Gradient Methods Can Take Exponential Time to Converge
The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For …
Policy Gradient MethodsFactored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs
Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient est…
Policy Gradient MethodsStrategic bidding in freight transport using deep reinforcement learning
This paper presents a multi-agent reinforcement learning algorithm to represent strategic bidding behavior in freight transport markets. Using this algorithm, we investigate whether feasible market equilibriums arise wit…
Deep Reinforcement LearningFairnessMulti-agent Reinforcement LearningPolicy Gradient Methods+3Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games
Policy-based methods with function approximation are widely used for solving two-player zero-sum games with large state and/or action spaces. However, it remains elusive how to obtain optimization and statistical guarant…
Policy Gradient MethodsVocal Bursts Valence PredictionIndependent Policy Gradient Methods for Competitive Reinforcement Learning
We obtain global, non-asymptotic convergence guarantees for independent learning algorithms in competitive reinforcement learning settings with two agents (i.e., zero-sum stochastic games). We consider an episodic settin…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Incremental Policy Gradients for Online Reinforcement Learning Control
Policy gradient methods are built on the policy gradient theorem, which involves a term representing the complete sum of rewards into the future: the return. Due to this, one usually either waits until the end of an epis…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)PGPS : Coupling Policy Gradient with Population-based Search
Gradient-based policy search algorithms (such as PPO, SAC or TD3) in deep reinforcement learning (DRL) have shown successful results on a range of challenging control tasks. However, they often suffer from flat or decept…
Deep Reinforcement LearningMuJoCoPolicy Gradient MethodsSelf-Supervised Continuous Control without Policy Gradient
Despite the remarkable progress made by the policy gradient algorithms in reinforcement learning (RL), sub-optimal policies usually result from the local exploration property of the policy gradient update. In this work, …
continuous-controlContinuous ControlMuJoCoPolicy Gradient Methods+32D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
3D convolutional networks are prevalent for video recognition. While achieving excellent recognition performance on standard benchmarks, they operate on a sequence of frames with 3D convolutions and thus are computationa…
Action RecognitionPolicy Gradient MethodsVideo RecognitionDifference Rewards Policy Gradients
Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit ass…
counterfactualMulti-agent Reinforcement LearningPolicy Gradient MethodsReinforcement Learning (RL)Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FEL
Reinforcement learning holds tremendous promise in accelerator controls. The primary goal of this paper is to show how this approach can be utilised on an operational level on accelerator physics problems. Despite the su…
Deep Reinforcement LearningmodelPolicy Gradient MethodsQ-Learning+3An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search
Deep reinforcement learning (DRL) algorithms and evolution strategies (ES) have been applied to various tasks, showing excellent performances. These have the opposite properties, with DRL having good sample efficiency an…
continuous-controlContinuous ControlDeep Reinforcement LearningPolicy Gradient Methods+3Sample Complexity of Policy Gradient Finding Second-Order Stationary Points
The goal of policy-based reinforcement learning (RL) is to search the maximal point of its objective. However, due to the inherent non-concavity of its objective, convergence to a first-order stationary point (FOSP) can …
Policy Gradient MethodsReinforcement Learning (RL)Learning Multi-Agent Communication through Structured Attentive Reasoning
Learning communication via deep reinforcement learning has recently been shown to be an effective way to solve cooperative multi-agent tasks. However, learning which communicated information is beneficial for each agent'…
Decision MakingDeep Reinforcement LearningMulti-agent Reinforcement LearningPolicy Gradient Methods+2