Data to 14 Oct 2026

Emergence of In-Context Reinforcement Learning from Noise Distillation

arXiv 2312.12275 ↗First posted 19 Dec 2023cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks. Current in-context RL methods are limited by their strict requirements for data, which needs to be generated by RL agents or labeled with actions from an optimal policy. In order to address this prevalent problem, we propose AD^varepsilon, a new data acquisition approach that enables in-context Reinforcement Learning from noise-induced curriculum. We show that it is viable to construct a synthetic noise injection curriculum which helps to obtain learning histories. Moreover, we experimentally demonstrate that it is possible to alleviate the need for generation using optimal policies, with in-context RL still able to outperform the best suboptimal policy in a learning dataset by a 2x margin.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 31 of its 46 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

31 of 46 references.

References · 31

2017Attention Is All You Needcited by 60,361
2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
2022Emergent Abilities of Large Language Modelscited by 2,512
2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
2022A Generalist Agentcited by 808
2022Transformers learn in-context by gradient descentcited by 732
2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
2016Learning to reinforcement learncited by 377

19 more

2021Transformers Can Do Bayesian Inferencecited by 360
2022Transformers are Sample-Efficient World Modelscited by 328
2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
2022Multi-Game Decision Transformerscited by 214
2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
2020The NetHack Learning Environmentcited by 198
2022In-context Reinforcement Learning with Algorithm Distillationcited by 190
2023Supervised Pretraining Can Learn In-Context Reinforcement Learningcited by 139
2022CORL: Research-oriented Deep Offline Reinforcement Learning Librarycited by 119
2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 105
2022Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RLcited by 103
2020Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learningcited by 65
2023Emergent Agentic Transformer from Chain of Hindsight Experiencecited by 33
2023Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulatorscited by 21
2022Dungeons and Data: A Large-Scale NetHack Datasetcited by 16
2023Transformers in Reinforcement Learning: A Surveycited by 12
2022Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learningcited by 11
2023Cross-Episodic Curriculum for Transformer Agentscited by 10
2023Katakomba: Tools and Benchmarks for Data-Driven NetHackcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 15; 2026: 4.

27 papers.

Sort:

By area:

2025Reward Is Enough: LLMs Are In-Context Reinforcement Learnerscited by 31
2023In-Context Reinforcement Learning for Variable Action Spacescited by 24
2024Retrieval-Augmented Decision Transformer: External Memory for In-context RLcited by 21
2024XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learningcited by 14
2025Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planningcited by 13
2025Vintix: Action Model via In-Context Reinforcement Learningcited by 10
2025Yes, Q-learning Helps Offline In-Context RLcited by 10
2025Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamicscited by 8
2025Mixture-of-Experts Meets In-Context Reinforcement Learningcited by 8
2024N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needscited by 7
2024Benchmarking General-Purpose In-Context Learningcited by 6
2025Filtering Learning Histories Enhances In-Context Reinforcement Learningcited by 5

15 more

2025Scalable In-Context Q-Learningcited by 5
2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worldscited by 4
2025Towards Provable Emergence of In-Context Reinforcement Learningcited by 3
2025Safe In-Context Reinforcement Learningcited by 3
2024Random Policy Enables In-Context Reinforcement Learning within Trust Horizonscited by 2
2025Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPscited by 2
2026Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamworkcited by 2
2024Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Modelscited by 1
2024HVAC-DPT: A Decision Pretrained Transformer for HVAC Controlcited by 1
2025Exploiting Policy Idling for Dexterous Manipulationcited by 1
2026Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learnercited by 1
2025Robust In-Context Reinforcement Learning Under Reward Poisoning Attackscited by 0
2025Context Value Informed In-Context Reinforcement Learningcited by 0
2026Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformerscited by 0
2026Scalable In-Context Reinforcement Learning with Recurrent Algorithm Distillationcited by 0