Papers with Code 아카이브

Offline RL

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

2

보존된 평가 기록

4

코드

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

https://github.com/denisyarats/exorl

공식 코드

Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning

https://github.com/desikrengarajan/fedora

공식 코드

Federated Ensemble-Directed Offline Reinforcement Learning

https://github.com/dmksjfl/CABI

공식 코드

Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination

https://github.com/dmksjfl/seabo

공식 코드

SEABO: A Simple Search-Based Method for Offline Imitation Learning

https://github.com/dohyeoklee/SPQR

공식 코드

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

https://github.com/dragon-zhuang/bppo

공식 코드

Behavior Proximal Policy Optimization

https://github.com/dragon-zhuang/reinformer

공식 코드

Reinformer: Max-Return Sequence Modeling for Offline RL

https://github.com/dsshim0125/s2p

공식 코드

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

https://github.com/dt6a/actoreg

공식 코드

The Role of Deep Learning Regularizations on Actors in Offline RL

https://github.com/dt6a/clorl

공식 코드

Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?

https://github.com/dt6a/rebrac

공식 코드

Revisiting the Minimalist Approach to Offline Reinforcement Learning

https://github.com/egg-west/mcep

공식 코드

Mildly Constrained Evaluation Policy for Offline Reinforcement Learning

https://github.com/elicassion/StARformer

공식 코드

StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning

https://github.com/emptyjackson/unifloral

공식 코드

A Clean Slate for Offline Reinforcement Learning

https://github.com/enajx/ndp

공식 코드

Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs

https://github.com/enjeeneer/conservative-world-models

공식 코드

Zero-Shot Reinforcement Learning from Low Quality Data

https://github.com/enjeeneer/zero-shot-rl

공식 코드

Zero-Shot Reinforcement Learning from Low Quality Data

https://github.com/eric-mitchell/macaw

공식 코드

Offline Meta-Reinforcement Learning with Advantage Weighting

https://github.com/ethanluoyc/optimal_transport_reward

공식 코드

Optimal Transport for Offline Imitation Learning

https://github.com/facebookresearch/drqv2

공식 코드

VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

https://github.com/facebookresearch/gen_dgrl

공식 코드

The Generalization Gap in Offline Reinforcement Learning

https://github.com/facebookresearch/latent-space-priors

공식 코드

Leveraging Demonstrations with Latent Space Priors

https://github.com/facebookresearch/mtm

공식 코드

Masked Trajectory Models for Prediction, Representation, and Control

https://github.com/facebookresearch/nle

공식 코드

Dungeons and Data: A Large-Scale NetHack Dataset

https://github.com/facebookresearch/ssorl

공식 코드

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

https://github.com/facebookresearch/vip

공식 코드

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

https://github.com/fangchenliu/maskdp_public

공식 코드

Masked Autoencoding for Scalable and Generalizable Decision Making

https://github.com/felix-thu/AlignIQL

공식 코드

AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization

https://github.com/felix-thu/DiffCPS

공식 코드

DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning

https://github.com/g0k0ururi/crop

공식 코드

CROP: Conservative Reward for Model-based Offline Policy Optimization

https://github.com/gabrielkmbo/explore-rl

공식 코드

Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs

https://github.com/gilesluo/reassessdtr

공식 코드

Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination

https://github.com/google-deepmind/dmc_vision_benchmark

공식 코드

DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors

https://github.com/google-research/batch_rl

공식 코드

An Optimistic Perspective on Offline Reinforcement Learning

https://github.com/google-research/google-research

공식 코드

Behavior Regularized Offline Reinforcement Learning

https://github.com/google-research/google-research/tree/master/experience_replay

공식 코드

Revisiting Fundamentals of Experience Replay

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