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/jajajang/lowpopart

공식 코드

Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits

https://github.com/jarridrb/dem

공식 코드

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities

https://github.com/jdreo/paradiseo

공식 코드

Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics ---22 Years of Paradiseo---

https://github.com/jjbong/strangeness_exploration

공식 코드

Strangeness-driven Exploration in Multi-Agent Reinforcement Learning

https://github.com/johnlyu2/z3alpha

공식 코드

Layered and Staged Monte Carlo Tree Search for SMT Strategy Synthesis

https://github.com/joseeliel/lightweight_genetic_algorithm

공식 코드

A diversity-enhanced genetic algorithm for efficient exploration of parameter spaces

https://github.com/juliagrosse/ults

공식 코드

Uncertainty-Guided Optimization on Large Language Model Search Trees

https://github.com/jungtaekkim/losan-lofav

공식 코드

Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization

https://github.com/junsu-kim97/higl

공식 코드

Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning

https://github.com/kaist-silab/symmetric_replay

공식 코드

Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization

https://github.com/kakaobrain/leco

공식 코드

LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward

https://github.com/katerakelly/oyster

공식 코드

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

https://github.com/kazizzad/BDQN-MxNet-Gluon

공식 코드

Efficient Exploration through Bayesian Deep Q-Networks

https://github.com/kclip/rg-pt

공식 코드

Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs

https://github.com/kirjner/ggs

공식 코드

Improving Protein Optimization with Smoothed Fitness Landscapes

https://github.com/lasgroup/gosafeopt

공식 코드

Tuning Legged Locomotion Controllers via Safe Bayesian Optimization

https://github.com/leanderdiazbone/discover

공식 코드

DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning

https://github.com/luchuanzhao/oto-planner

공식 코드

OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown Environments

https://github.com/luisvargasmieles/ls-mcmc

공식 코드

The split Gibbs sampler revisited: improvements to its algorithmic structure and augmented target distribution

https://github.com/lyneyandlynette/GoBI

공식 코드

Go Beyond Imagination: Maximizing Episodic Reachability with World Models

https://github.com/mahaa2/embeddedlmc

공식 코드

Lagrangian Manifold Monte Carlo on Monge Patches

https://github.com/maho3/ltu-ili

공식 코드

LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology

https://github.com/manish-pra/sagempc

공식 코드

Safe Guaranteed Exploration for Non-linear Systems

https://github.com/mcmachado/count_based_exploration_sr

공식 코드

Count-Based Exploration with the Successor Representation

https://github.com/med-air/dex

공식 코드

Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

https://github.com/microsoft/strategically_efficient_rl

공식 코드

Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning

https://github.com/microsoft/tracecodegen

공식 코드

Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions

https://github.com/mila-iqia/DeepDrummer

공식 코드

DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the Loop

https://github.com/mschulth/rhc

공식 코드

Receding Horizon Curiosity

https://github.com/my-name-is-D/high_level_nav_planning

공식 코드

Learning Dynamic Cognitive Map with Autonomous Navigation

https://github.com/nighood/SynAlign

공식 코드

Few-shot_LLM_Synthetic_Data_with_Distribution_Matching

https://github.com/nikonikolov/rltf

공식 코드

Information-Directed Exploration for Deep Reinforcement Learning

https://github.com/nnaisense/max

공식 코드

Model-Based Active Exploration

https://github.com/nojhan/paradiseo

공식 코드

Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics ---22 Years of Paradiseo---

https://github.com/oxwhirl/opiq

공식 코드

Optimistic Exploration even with a Pessimistic Initialisation

https://github.com/pathak22/exploration-by-disagreement

공식 코드

Self-Supervised Exploration via Disagreement

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