paper-with-me

홈 › Papers

Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning

2018-09-18 · Izumi Karino, Kazutoshi Tanaka, Ryuma Niiyama, Yasuo Kuniyoshi

This paper proposes an exploration method for deep reinforcement learning based on parameter space noise. Recent studies have experimentally shown that parameter space noise results in better exploration than the commonly used action space noise. Previous methods devised a way to update the diagonal covariance matrix of a noise distribution and did not consider the direction of the noise vector and its correlation. In addition, fast updates of the noise distribution are required to facilitate policy learning. We propose a method that deforms the noise distribution according to the accumulated returns and the noises that have led to the returns. Moreover, this method switches isotropic exploration and directional exploration in parameter space with regard to obtained rewards. We validate our exploration strategy in the OpenAI Gym continuous environments and modified environments with sparse rewards. The proposed method achieves results that are competitive with a previous method at baseline tasks. Moreover, our approach exhibits better performance in sparse reward environments by exploration with the switching strategy.

📄 PDF Abstract BibTeX arXiv:1809.06570

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts

2026-02-22 · Toshihide Ubukata, Zhiyao Wang, Enhong Mu, Jialong Li 외 arxiv

On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement le…

Zero-shot GeneralizationReinforcement Learning

Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift

2026-05-06 · Jonathan R. Landers arxiv

We study long-horizon deployment of a frozen predictor under dynamic covariate shift. A time-domain Poincare inequality first reduces temporal risk volatility to derivative energy. A Jacobian-velocity theorem then suppli…

Hyperbolic Diffusion Recommender Model

2025-04-02 · Meng Yuan, Yutian Xiao, Wei Chen, Chu Zhao 외

Diffusion models (DMs) have emerged as the new state-of-the-art family of deep generative models. To gain deeper insights into the limitations of diffusion models in recommender systems, we investigate the fundamental st…

modelRecommendation Systems

When should agents explore?

2021-08-26 · NeurIPS 2021 12 · Miruna Pîslar, David Szepesvari, Georg Ostrovski, Diana Borsa 외

Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a monolithic behaviour policy that changes only gradually (at best). In contrast, the explorato…

DiversityReinforcement Learning (RL)

Bias Correction in Deterministic Policy Gradient Using Robust MPC

2021-04-06 · Arash Bahari Kordabad, Hossein Nejatbakhsh Esfahani, Sebastien Gros

In this paper, we discuss the deterministic policy gradient using the Actor-Critic methods based on the linear compatible advantage function approximator, where the input spaces are continuous. When the policy is restric…

Model Predictive Control