Papers with Code 아카이브

D4RL

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

9

코드

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

https://github.com/linhlpv/Offline-and-OfflineOnline-RL

Offline Reinforcement Learning with Implicit Q-Learning

https://github.com/lions-epfl/lion

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

https://github.com/lucashueda/long_sentence_transformer

Reformer: The Efficient Transformer

https://github.com/lucidrains/linear-attention-transformer

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

https://github.com/lucidrains/performer-pytorch

Rethinking Attention with Performers

https://github.com/lucidrains/reformer-pytorch

Reformer: The Efficient Transformer

https://github.com/microsoft/lightatac

Adversarially Trained Actor Critic for Offline Reinforcement Learning

https://github.com/ml-jku/l2m

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/mpatacchiola/imujoco

D4RL: Datasets for Deep Data-Driven Reinforcement Learning

https://github.com/nikhilbarhate99/min-decision-transformer

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/opendilab/DI-engine

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/orrivlin/implicit-q-learning

Offline Reinforcement Learning with Implicit Q-Learning

https://github.com/perrin-isir/afu

Offline Reinforcement Learning with Implicit Q-Learning

https://github.com/pwc-1/Paper-10/tree/main/transformer

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

https://github.com/pwc-1/Paper-8/tree/main/decision_transformer

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/pytorch/rl/tree/main/examples/decision_transformer

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/pytorch/rl/tree/main/examples/iql

Offline Reinforcement Learning with Implicit Q-Learning

https://github.com/quantumiracle/consistency_model_for_reinforcement_learning

Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning

https://github.com/ran-weii/cleanil

Implicit Behavioral Cloning

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

d3rlpy: An Offline Deep Reinforcement Learning Library

https://github.com/sliao-mi-luku/Chatbot-Reformer

Reformer: The Efficient Transformer

https://github.com/sliao-mi-luku/NLP-Chatbot-Reformer-Trax

Reformer: The Efficient Transformer

https://github.com/snu-mllab/edac

Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble

https://github.com/teddykoker/performer

Rethinking Attention with Performers

https://github.com/tensorflow/models/tree/master/official/nlp/modeling

Rethinking Attention with Performers

https://github.com/thibaultdouzon/long-range-document-transformer

cosFormer: Rethinking Softmax in Attention

https://github.com/typoverflow/OfflineRL-Lib

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/xavierchanglingli/regularized-optimal-experience-replay

Extreme Q-Learning: MaxEnt RL without Entropy

https://github.com/xl402/performer

Rethinking Attention with Performers

https://github.com/yangyucheng000/University/tree/main/model-3/reformer

Reformer: The Efficient Transformer

https://github.com/yifan123/arxiv_spider

False Correlation Reduction for Offline Reinforcement Learning

https://github.com/yihaosun1124/OfflineRL-Kit

Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble

https://github.com/yiqinyang/vem

Offline Reinforcement Learning with Value-based Episodic Memory

https://github.com/yun-kwak/decision-transformer-jax

Decision Transformer: Reinforcement Learning via Sequence Modeling

https://github.com/zzmtsvv/ORL

Mildly Conservative Q-Learning for Offline Reinforcement Learning

https://github.com/zzmtsvv/rl_task

Decision Transformer: Reinforcement Learning via Sequence Modeling

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