Papers with Code 아카이브

Reinforcement Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

162

보존된 평가 기록

1

코드

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

https://github.com/shreyesss/PPO-implementation-keras-tensorflow

High-Dimensional Continuous Control Using Generalized Advantage Estimation

https://github.com/shriram2112/Reinforcement_learning_gym

OpenAI Gym

https://github.com/shubhamgupta5893/GraphRNN

MolecularRNN: Generating realistic molecular graphs with optimized properties

https://github.com/shubhamguptaiitd/GraphRNN

MolecularRNN: Generating realistic molecular graphs with optimized properties

https://github.com/shucheng-liu/TensorFlow_CAM

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

https://github.com/shuishida/soaprl

Proximal Policy Optimization Algorithms

https://github.com/shuli0808/DQN

A Distributional Perspective on Reinforcement Learning

https://github.com/shunzh/pytorch-maml-rl

RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning

https://github.com/shyamal-anadkat/offlinerl

d3rlpy: An Offline Deep Reinforcement Learning Library

https://github.com/shyamsn97/controllable-ncas

HyperNCA: Growing Developmental Networks with Neural Cellular Automata

https://github.com/shyamsn97/hyper-nn

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

https://github.com/shyhyawJou/Grad-CAM-pytorch

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

https://github.com/shyhyawJou/GradCAM-Tensorflow

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

https://github.com/sibeshkar/gym

OpenAI Gym

https://github.com/sicara/tf-explain

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

https://github.com/siddharthnishtala/DQN-Trader

Deep reinforcement learning for time series: playing idealized trading games

https://github.com/siddharthverma314/proximalpolicyoptimization

Proximal Policy Optimization Algorithms

https://github.com/siddikui/Fast-DARTS

DARTS: Differentiable Architecture Search

https://github.com/sidney1505/arc_maml_transformer

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

https://github.com/silvadenisaraujo/OpenAIGym-Taxi-v2

Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition

https://github.com/silvialuu/DRL-2018

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

https://github.com/simoll/apo

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

https://github.com/simsal0r/mixture-of-decision-trees

MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning

https://github.com/simsimiSION/pymarl-algorithm-extension-via-starcraft

The StarCraft Multi-Agent Challenge

https://github.com/sinaghiassian/OffpolicyAlgorithms

Investigating practical linear temporal difference learning

https://github.com/sinamoradian/SNIP-NAS-2

DARTS: Differentiable Architecture Search

https://github.com/singh-shakti94/Deep-Learning-Project

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

https://github.com/sino30535/Weak-label-in-CT-image-segamentation

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

https://github.com/sinsauzero/buildblock-env-of-pybullet

Efficient Bimanual Manipulation Using Learned Task Schemas

https://github.com/sirakik/mprg_fc

Proximal Policy Optimization Algorithms

https://github.com/sirakik/ppo_football

Proximal Policy Optimization Algorithms

https://github.com/sisl/gail-driver

Benchmarking Deep Reinforcement Learning for Continuous Control

https://github.com/sisl/ngsim_env

Generative Adversarial Imitation Learning

https://github.com/siyuofzhou/DDPG

Continuous control with deep reinforcement learning

https://github.com/sjYoondeltar/IQN_example

Hindsight Experience Replay

https://github.com/sjYoondeltar/myRL_example

Hindsight Experience Replay

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