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/google-research/google-research/tree/master/multi_game_dt

공식 코드

Multi-Game Decision Transformers

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

공식 코드

RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning

https://github.com/google/trax/tree/master/trax/models/reformer

공식 코드

Reformer: The Efficient Transformer

https://github.com/guoyihonggyh/mobody-model-based-off-dynamics-offline-reinforcement-learning

공식 코드

MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning

https://github.com/hakuhodo-technologies/scope-rl

공식 코드

SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation

https://github.com/hari-sikchi/DVL

공식 코드

Dual RL: Unification and New Methods for Reinforcement and Imitation Learning

https://github.com/hemerson1/offline-glucose

공식 코드

Offline Reinforcement Learning for Safer Blood Glucose Control in People with Type 1 Diabetes

https://github.com/hmomin/networkgym

공식 코드

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation

https://github.com/holarissun/rewardshifting

공식 코드

Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping

https://github.com/hori-group/two-step-design

공식 코드

Two-step reinforcement learning for model-free redesign of nonlinear optimal regulator

https://github.com/huawei-noah/HEBO/tree/master/PMDB

공식 코드

Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief

https://github.com/huawei-noah/hebo

공식 코드

Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief

https://github.com/huihuichyan/think-j

공식 코드

Think-J: Learning to Think for Generative LLM-as-a-Judge

https://github.com/hukz18/defog

공식 코드

Decision Transformer under Random Frame Dropping

https://github.com/hwang-ua/inac_pytorch

공식 코드

The In-Sample Softmax for Offline Reinforcement Learning

https://github.com/idiap/fast-transformers

공식 코드

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

https://github.com/ikostrikov/implicit_q_learning

공식 코드

Offline Reinforcement Learning with Implicit Q-Learning

https://github.com/imoneoi/RSP_JAX

공식 코드

Are Expressive Models Truly Necessary for Offline RL?

https://github.com/improbable-ai/harness-offline-rl

공식 코드

Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting

https://github.com/jaewoopudding/gta

공식 코드

GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning

https://github.com/jasonma2016/gofar

공식 코드

Swapped goal-conditioned offline reinforcement learning

https://github.com/jhu-lcsr/costar_plan

공식 코드

The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints

https://github.com/johannesack/offlinerlstructurednonstationarity

공식 코드

Offline Reinforcement Learning from Datasets with Structured Non-Stationarity

https://github.com/junming-yang/moan

공식 코드

Model-based Offline Policy Optimization with Adversarial Network

https://github.com/jwhj/oreo

공식 코드

Offline Reinforcement Learning for LLM Multi-Step Reasoning

https://github.com/jzitovsky/sbv

공식 코드

Revisiting Bellman Errors for Offline Model Selection

https://github.com/kaixhin/gudrl

공식 코드

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

https://github.com/kasunweerkoon/VAPOR

공식 코드

VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning

https://github.com/kevinzhou497/distcb

공식 코드

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

https://github.com/khatch31/laeo

공식 코드

Contrastive Example-Based Control

https://github.com/kvfrans/cfgrl

공식 코드

Diffusion Guidance Is a Controllable Policy Improvement Operator

https://github.com/kvfrans/fre

공식 코드

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

https://github.com/kzl/decision-transformer

공식 코드

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/lamda-rl/imaginebench

공식 코드

ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts

https://github.com/lamda-rl/prdc

공식 코드

Policy Regularization with Dataset Constraint for Offline Reinforcement Learning

https://github.com/larocs/offline-rl-suvey

공식 코드

A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems

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