Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Sepp Hochreiter — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Sepp Hochreiter
27
papers ·
4075
citations ·
53
h-index
Johannes Kepler University of Linz · Apple (Israel) · Linz Center of Mechatronics (Austria)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
RUDDER: Return Decomposition for Delayed Rewards
2018 · 60 citations
History Compression via Language Models in Reinforcement Learning
2022 · 4 citations
Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning
2022 · 3 citations
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
2024 · 2 citations
A Dataset Perspective on Offline Reinforcement Learning
2021 · 2 citations
Learning to Modulate pre-trained Models in RL
2023 · 1 citations
RREDCoT: Segment-Level Reward Redistribution for Reasoning Models
2026
Retrieval-Augmented Decision Transformer: External Memory for In-context RL
2024
Contrastive Abstraction for Reinforcement Learning
2024
Top co-authors
Vihang Patil
· 6
Fabian Paischer
· 4
Markus Hofmarcher
· 4
Thomas Schmied
· 4
Angela Bitto-Nemling
· 3
Hamid Eghbal-zadeh
· 3
Razvan Pascanu
· 3
Johannes Brandstetter
· 2
Kajetan Schweighofer
· 2
Marius-Constantin Dinu
· 2
Andreas Radler
· 1
Christian Steinparz
· 1
Topics
Value-Based
Meta-RL
Model-Based RL
Policy Gradient
Offline RL
Game AI
Exploration
RLHF & Alignment
Safe RL