paper-with-me

Papers

Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies

2015-09-10 · David Balduzzi, Muhammad Ghifary

This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstly, we present a temporal-difference based method for learning the gradient of the value-function. Secondly, we present the deviator-actor-critic (DAC) model, which comprises three neural networks that estimate the value function, its gradient, and determine the actor's policy respectively. We evaluate GProp on two challenging tasks: a contextual bandit problem constructed from nonparametric regression datasets that is designed to probe the ability of reinforcement learning algorithms to accurately estimate gradients; and the octopus arm, a challenging reinforcement learning benchmark. GProp is competitive with fully supervised methods on the bandit task and achieves the best performance to date on the octopus arm.

📄 PDF Abstract BibTeX arXiv:1509.03005

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Flow Matching Policy Gradients

2025-07-28 · David McAllister, Songwei Ge, Brent Yi, Chung Min Kim 외 arxiv

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement…

Reinforcement LearningContinuous Control

Tail-Likelihood Reinforcement Learning

2026-09-02 · Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar, Guanning Zeng 외 arxiv

Reinforcement learning typically optimizes average reward. For generative policies, the average can hide an important distinction: two policies can achieve the same mean reward while having very different chances of prod…

Reinforcement LearningObject Localization

Deterministic Policy Gradient for Reinforcement Learning with Continuous Time and State

2025-09-28 · Ziheng Cheng, Xin Guo, Yufei Zhang arxiv

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL …

General Reinforcement Learning

Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients

2021-09-24 · Baturay Saglam, Furkan Burak Mutlu, Dogan Can Cicek, Suleyman Serdar Kozat

Approximation of the value functions in value-based deep reinforcement learning induces overestimation bias, resulting in suboptimal policies. We show that when the reinforcement signals received by the agents have a hig…

continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCo+2

Statistically Efficient Bayesian Sequential Experiment Design via Reinforcement Learning with Cross-Entropy Estimators

2023-05-29 · Tom Blau, Iadine Chades, Amir Dezfouli, Daniel Steinberg 외

Reinforcement learning can learn amortised design policies for designing sequences of experiments. However, current amortised methods rely on estimators of expected information gain (EIG) that require an exponential numb…

reinforcement-learning