# Context Value Informed In-Context Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.23209 · HTML: https://mlsanity.com/paper/2509.23209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 21 of its 22 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Data Distributional Properties Drive Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2205.05055/) (2022)
- [In-context Reinforcement Learning with Algorithm Distillation](https://mlsanity.com/paper/2210.14215/) (2022)
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://mlsanity.com/paper/2206.13499/) (2022)
- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents](https://mlsanity.com/paper/2310.09971/) (2023)
- [Generalization to New Sequential Decision Making Tasks with In-Context Learning](https://mlsanity.com/paper/2312.03801/) (2023)
- [Emergent Agentic Transformer from Chain of Hindsight Experience](https://mlsanity.com/paper/2305.16554/) (2023)
- [Training a Generally Curious Agent](https://mlsanity.com/paper/2502.17543/) (2025)
- [Emergence of In-Context Reinforcement Learning from Noise Distillation](https://mlsanity.com/paper/2312.12275/) (2023)
- [In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought](https://mlsanity.com/paper/2405.20692/) (2024)
- [AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers](https://mlsanity.com/paper/2411.11188/) (2024)
- [Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective](https://mlsanity.com/paper/2305.18464/) (2023)
- [Yes, Q-learning Helps Offline In-Context RL](https://mlsanity.com/paper/2502.17666/) (2025)
- [Scalable In-Context Q-Learning](https://mlsanity.com/paper/2506.01299/) (2025)

## Abstract (arXiv)

In-context reinforcement learning (ICRL) has emerged as an effective paradigm for test time adaptation to unseen tasks without parameter updates. However, existing ICRL methods can exhibit brittle and unstable adaptions, and the mechanisms underlying such adaptions remain poorly understood. We provide a policy-gradient view of ICRL and argue that relying on trajectory-level return feedback can lead to high-variance updates when test time rollout is limited. Motivated by the actor--critic principle, we propose Context Value Informed ICRL (CV-ICRL), which equips the in-context policy with an explicit context value: the expected discounted return conditioned on the current state and accumulated interaction context. CV-ICRL trains a value head and writes its prediction back into the context as a value token, enabling TD-style return targets for lower-variance policy updates. Experiments on the Dark Room, Minigrid, and Procgen testbeds show that CV-ICRL substantially improves the stability of test time adaptation and achieves higher returns across tasks and environments. Code and data are available at https://github.com/Bluixe/CV-ICRL .