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/011235813/cm3

공식 코드

CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning

https://github.com/18979705623/hspr

공식 코드

Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation

https://github.com/3it-inpaqt/dot-calibration-v2

공식 코드

Robust quantum dots charge autotuning using neural network uncertainty

https://github.com/AdriaJ/PolyatomicFW_SPL

공식 코드

A Fast and Scalable Polyatomic Frank-Wolfe Algorithm for the LASSO

https://github.com/AmmarFayad/Behavioral-Actor-Critic

공식 코드

Behavior-Guided Actor-Critic: Improving Exploration via Learning Policy Behavior Representation for Deep Reinforcement Learning

https://github.com/Arashkhajooei/Meta-Learning-Integration-in-Hierarchical-Reinforcement-Learning-for-Advanced-Task-Complexity

공식 코드

Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity

https://github.com/Baichenjia/OB2I

공식 코드

Principled Exploration via Optimistic Bootstrapping and Backward Induction

https://github.com/FlorenceFeng/StateDecoding

공식 코드

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

https://github.com/GPaolo/SERENE

공식 코드

Sparse Reward Exploration via Novelty Search and Emitters

https://github.com/HIPS/molecule-autoencoder

공식 코드

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

https://github.com/IBM/sau-explore

공식 코드

Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks

https://github.com/IndustAI/risk-and-uncertainty

공식 코드

Estimating Risk and Uncertainty in Deep Reinforcement Learning

https://github.com/Lyuliyao/consensus-sampling-method-for-expolering-high-dimensional-energy-surface

공식 코드

Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes

https://github.com/MilesTime/Reward-Centered-ReST-MCTS

공식 코드

Reward-Centered ReST-MCTS: A Robust Decision-Making Framework for Robotic Manipulation in High Uncertainty Environments

https://github.com/NYU-MLDA/scarl

공식 코드

ASCENT: Amplifying Power Side-Channel Resilience via Learning & Monte-Carlo Tree Search

https://github.com/NagisaZj/MetaCURE-Public

공식 코드

MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration

https://github.com/NanxuGong/ELLM-FT

공식 코드

Evolutionary Large Language Model for Automated Feature Transformation

https://github.com/RenMing-Huang/EGR-PO

공식 코드

Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance

https://github.com/RonanFR/UCRL

공식 코드

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

https://github.com/ScalableSamplingInLargeDatabases/QPlus

공식 코드

Scalable Sampling for High Utility Patterns

https://github.com/Usama1002/EBE-Exploration

공식 코드

Learning-Driven Exploration for Reinforcement Learning

https://github.com/WenboGong/MetaSGMCMC

공식 코드

Meta-Learning for Stochastic Gradient MCMC

https://github.com/Zhengbo-Zhang/ITKD

공식 코드

Instance Temperature Knowledge Distillation

https://github.com/aditya-ramesh-10/exploring-through-rcgvf

공식 코드

Exploring through Random Curiosity with General Value Functions

https://github.com/agaier/sail_gecco2017

공식 코드

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

https://github.com/aklein1995/heterogeneous_agents_curiosity_vizdoom

공식 코드

Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?

https://github.com/alimama-creative/AES-Adaptive-and-Efficient-ad-creative-Selection

공식 코드

Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure

https://github.com/alstn12088/adaptive-teacher

공식 코드

Adaptive teachers for amortized samplers

https://github.com/amazon-research/multimodal-neuralslam

공식 코드

Learning to Act with Affordance-Aware Multimodal Neural SLAM

https://github.com/amine179/curiosity-rl-for-drug-design

공식 코드

Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design

https://github.com/an-on-ym-ous/lbn_mobo

공식 코드

Large-Batch, Iteration-Efficient Neural Bayesian Design Optimization

https://github.com/aria-systems-group/hsvi-rp

공식 코드

Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives

https://github.com/aslanides/aixijs

공식 코드

Count-Based Exploration in Feature Space for Reinforcement Learning

https://github.com/aspuru-guzik-group/chemical_vae

공식 코드

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

https://github.com/astrid-merckling/SRL4RL

공식 코드

Exploratory State Representation Learning

https://github.com/baai-agents/cradle

공식 코드

Cradle: Empowering Foundation Agents Towards General Computer Control

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