# Generalization to New Sequential Decision Making Tasks with In-Context Learning

arXiv: https://arxiv.org/abs/2312.03801 · HTML: https://mlsanity.com/paper/2312.03801/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 87 references that are in the map.
- First posted on arXiv 6 Dec 2023.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Reinforcement Learning with Augmented Data](https://mlsanity.com/paper/2004.14990/) (2020)
- [Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents](https://mlsanity.com/paper/1709.06009/) (2017)
- [Multi-Game Decision Transformers](https://mlsanity.com/paper/2205.15241/) (2022)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [The NetHack Learning Environment](https://mlsanity.com/paper/2006.13760/) (2020)
- [Online Decision Transformer](https://mlsanity.com/paper/2202.05607/) (2022)
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://mlsanity.com/paper/2206.13499/) (2022)
- [TransDreamer: Reinforcement Learning with Transformer World Models](https://mlsanity.com/paper/2202.09481/) (2022)
- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [Structured State Space Models for In-Context Reinforcement Learning](https://mlsanity.com/paper/2303.03982/) (2023)
- [A Tutorial on Meta-Reinforcement Learning](https://mlsanity.com/paper/2301.08028/) (2023)
- [General-Purpose In-Context Learning by Meta-Learning Transformers](https://mlsanity.com/paper/2212.04458/) (2022)
- [Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL](https://mlsanity.com/paper/2209.03993/) (2022)

## Built on by (most cited first, 30 of 39)

- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks](https://mlsanity.com/paper/2410.23208/) (2024)
- [LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities](https://mlsanity.com/paper/2504.16078/) (2025)
- [EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration](https://mlsanity.com/paper/2410.06238/) (2024)
- [LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations](https://mlsanity.com/paper/2412.01441/) (2024)
- [Training a Generally Curious Agent](https://mlsanity.com/paper/2502.17543/) (2025)
- [Reward Is Enough: LLMs Are In-Context Reinforcement Learners](https://mlsanity.com/paper/2506.06303/) (2025)
- [LLMs Are In-Context Bandit Reinforcement Learners](https://mlsanity.com/paper/2410.05362/) (2024)
- [In-Context Reinforcement Learning for Variable Action Spaces](https://mlsanity.com/paper/2312.13327/) (2023)
- [RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models](https://mlsanity.com/paper/2508.02062/) (2025)
- [Retrieval-Augmented Decision Transformer: External Memory for In-context RL](https://mlsanity.com/paper/2410.07071/) (2024)
- [Efficient Sequential Decision Making with Large Language Models](https://mlsanity.com/paper/2406.12125/) (2024)
- [REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments](https://mlsanity.com/paper/2412.04759/) (2024)
- [AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers](https://mlsanity.com/paper/2411.11188/) (2024)
- [XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning](https://mlsanity.com/paper/2406.08973/) (2024)
- [A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks](https://mlsanity.com/paper/2410.22391/) (2024)
- [Formalizing Learning from Language Feedback with Provable Guarantees](https://mlsanity.com/paper/2506.10341/) (2025)
- [CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing](https://mlsanity.com/paper/2410.16670/) (2024)
- [Yes, Q-learning Helps Offline In-Context RL](https://mlsanity.com/paper/2502.17666/) (2025)
- [Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens](https://mlsanity.com/paper/2411.05189/) (2024)
- [Should You Use Your Large Language Model to Explore or Exploit?](https://mlsanity.com/paper/2502.00225/) (2025)
- [ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?](https://mlsanity.com/paper/2608.03874/) (2026)
- [ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI](https://mlsanity.com/paper/2410.02751/) (2024)
- [Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL](https://mlsanity.com/paper/2602.04089/) (2026)
- [Behavioral Exploration: Learning to Explore via In-Context Adaptation](https://mlsanity.com/paper/2507.09041/) (2025)
- [In-Context Reinforcement Learning via Communicative World Models](https://mlsanity.com/paper/2508.06659/) (2025)
- [Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction](https://mlsanity.com/paper/2402.04154/) (2024)
- [Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds](https://mlsanity.com/paper/2502.02869/) (2025)
- [Comparing Exploration-Exploitation Strategies of LLMs and Humans: Insights from Standard Multi-armed Bandit Experiments](https://mlsanity.com/paper/2505.09901/) (2025)
- [Safe In-Context Reinforcement Learning](https://mlsanity.com/paper/2509.25582/) (2025)

## Abstract (arXiv)

Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to learn new language or vision tasks without any weight updates from only a few examples, also referred to as in-context learning. However, the sequential decision making setting poses additional challenges having a lower tolerance for errors since the environment's stochasticity or the agent's actions can lead to unseen, and sometimes unrecoverable, states. In this paper, we use an illustrative example to show that naively applying transformers to sequential decision making problems does not enable in-context learning of new tasks. We then demonstrate how training on sequences of trajectories with certain distributional properties leads to in-context learning of new sequential decision making tasks. We investigate different design choices and find that larger model and dataset sizes, as well as more task diversity, environment stochasticity, and trajectory burstiness, all result in better in-context learning of new out-of-distribution tasks. By training on large diverse offline datasets, our model is able to learn new MiniHack and Procgen tasks without any weight updates from just a handful of demonstrations.