Papers with Code 아카이브

Efficient Exploration

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.

Source: Randomized Value Functions via Multiplicative Normalizing Flows

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/xiaoaoran/3d_label_efficient_learning

공식 코드

A Survey of Label-Efficient Deep Learning for 3D Point Clouds

https://github.com/xwhan/walk_the_blocks

공식 코드

Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents

https://github.com/yazaazou/galaxy-band-conversion

공식 코드

Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep Learning

https://github.com/yexf308/ATLAS

공식 코드

Nonlinear model reduction for slow-fast stochastic systems near unknown invariant manifolds

https://github.com/yfletberliac/adversarially-guided-actor-critic

공식 코드

Adversarially Guided Actor-Critic

https://github.com/yingfan-bot/mbpsrl

공식 코드

Model-based Reinforcement Learning for Continuous Control with Posterior Sampling

https://github.com/yjwang0618/subgoal-based-exploration

공식 코드

Dynamic Subgoal-based Exploration via Bayesian Optimization

https://github.com/zaparolicunha/stl_surrogate

공식 코드

On Machine Learning-Driven Surrogates for Sound Transmission Loss Simulations

https://github.com/zcrabbit/vbpi-torch

공식 코드

A Variational Approach to Bayesian Phylogenetic Inference

https://github.com/zjwzcx/GenNBV

공식 코드

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction

https://github.com/zoharri/mamba

공식 코드

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

https://gitlab.com/tomblau/Bayesian-Curiosity

공식 코드

Bayesian Curiosity for Efficient Exploration in Reinforcement Learning

https://github.com/2016choang/sfl

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning

https://github.com/ARiSE-Lab/ConEX__Replication_Package

ConEx: Efficient Exploration of Big-Data System Configurations for Better Performance

https://github.com/BY571/DQN-Atari-Agents

Noisy Networks for Exploration

https://github.com/Clyde21c/PEARL_bullet

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

https://github.com/Curt-Park/rainbow-is-all-you-need

Noisy Networks for Exploration

https://github.com/HarriBellThomas/VDQN

Variational Deep Q Network

https://github.com/Ishan-Kumar2/Molecular_VAE_Pytorch

Automatic chemical design using a data-driven continuous representation of molecules

https://github.com/JanKruska/sail

Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination

https://github.com/JavierAntoran/Bayesian-Neural-Networks

Stochastic Gradient Hamiltonian Monte Carlo

https://github.com/Kaixhin/NoisyNet-A3C

Noisy Networks for Exploration

https://github.com/LilTwo/DRL-using-PyTorch

Noisy Networks for Exploration

https://github.com/MOVzeroOne/DQN

Noisy Networks for Exploration

https://github.com/MindSpore-scientific-2/code-3/tree/main/stochastic-attention-head-removal-a-simple

Stochastic Gradient Hamiltonian Monte Carlo

https://github.com/NervanaSystems/coach

Deep Exploration via Bootstrapped DQN

https://github.com/RLAgent/state-marginal-matching

Efficient Exploration via State Marginal Matching

https://github.com/Sascha0912/SAIL

Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination

https://github.com/SheffieldML/GPyOpt

Batch Bayesian Optimization via Local Penalization

https://github.com/TrentBrick/PAE

Automatic chemical design using a data-driven continuous representation of molecules

https://github.com/TurboFreeze/sghmc

Stochastic Gradient Hamiltonian Monte Carlo

https://github.com/YanSong97/Master-thesis

Noisy Networks for Exploration

https://github.com/adaptive-intelligent-robotics/dcg-map-elites

Scaling MAP-Elites to Deep Neuroevolution

https://github.com/agaier/sail

Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination

https://github.com/aksub99/molecular-vae

Automatic chemical design using a data-driven continuous representation of molecules

https://github.com/behzadanksu/rl-attack

Noisy Networks for Exploration

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.