Papers In-Context Reinforcement Learning
“In-Context Reinforcement Learning” 태그가 달린 논문 33편 · 필터 해제
From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers
Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learning algorithms that rely on incremental va…
In-Context LearningIn-Context Reinforcement Learningreinforcement-learningReinforcement LearningScaling Algorithm Distillation for Continuous Control with Mamba
Algorithm Distillation (AD) was recently proposed as a new approach to perform In-Context Reinforcement Learning (ICRL) by modeling across-episodic training histories autoregressively with a causal transformer model. How…
continuous-controlContinuous ControlIn-Context Reinforcement LearningMamba+3Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?
We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al., 2023). To address the challenge of reward poisoning attacks targeting the …
In-Context Reinforcement LearningFiltering Learning Histories Enhances In-Context Reinforcement Learning
Transformer models (TMs) have exhibited remarkable in-context reinforcement learning (ICRL) capabilities, allowing them to generalize to and improve in previously unseen environments without re-training or fine-tuning. T…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningKnowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
Retrieval Augmented Generation (RAG) has shown strong capability in enhancing language models' knowledge and reducing AI generative hallucinations, driving its widespread use. However, complex tasks requiring multi-round…
In-Context Reinforcement LearningRAGRetrievalRetrieval-augmented GenerationFree Random Projection for In-Context Reinforcement Learning
Hierarchical inductive biases are hypothesized to promote generalizable policies in reinforcement learning, as demonstrated by explicit hyperbolic latent representations and architectures. Therefore, a more flexible appr…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningDistilling Reinforcement Learning Algorithms for In-Context Model-Based Planning
Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However,…
In-Context Reinforcement LearningReinforcement Learning (RL)Yes, Q-learning Helps Offline In-Context RL
Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL settings. In this study, we explore the int…
In-Context Reinforcement LearningMuJoCoOffline RLQ-Learning+1A Survey of In-Context Reinforcement Learning
Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1OmniRL: In-Context Reinforcement Learning by Large-Scale Meta-Training in Randomized Worlds
We introduce OmniRL, a highly generalizable in-context reinforcement learning (ICRL) model that is meta-trained on hundreds of thousands of diverse tasks. These tasks are procedurally generated by randomizing state trans…
Few-Shot LearningImitation LearningIn-Context LearningIn-Context Reinforcement Learning+4Vintix: Action Model via In-Context Reinforcement Learning
In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt co…
Decision MakingIn-Context Reinforcement Learningreinforcement-learningReinforcement LearningAn Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising
In online advertising, advertisers commonly utilize auto-bidding services to bid for impression opportunities. A typical objective of the auto-bidder is to optimize the advertiser's cumulative value of winning impression…
In-Context Reinforcement LearningSequential Decision MakingRL + Transformer = A General-Purpose Problem Solver
What if artificial intelligence could not only solve problems for which it was trained but also learn to teach itself to solve new problems (i.e., meta-learn)? In this study, we demonstrate that a pre-trained transformer…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningGUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration
Graphical User Interface (GUI) action grounding is a critical step in GUI automation that maps language instructions to actionable elements on GUI screens. Most recent works of GUI action grounding leverage large GUI dat…
In-Context Reinforcement LearningHVAC-DPT: A Decision Pretrained Transformer for HVAC Control
Building operations consume approximately 40% of global energy, with Heating, Ventilation, and Air Conditioning (HVAC) systems responsible for up to 50% of this consumption. As HVAC energy demands are expected to rise, o…
In-Context Reinforcement LearningReinforcement Learning (RL)Random Policy Enables In-Context Reinforcement Learning within Trust Horizons
Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in…
In-Context LearningIn-Context Reinforcement Learningreinforcement-learningReinforcement Learning+2Honesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Previous work has shown that training "helpful-only" LLMs with reinforcement learning on a curriculum of gameable environments can lead models to generalize to egregious specification gaming, such as editing their own re…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningLLMs Are In-Context Bandit Reinforcement Learners
Large Language Models (LLMs) excel at in-context learning (ICL), a supervised learning technique that relies on adding annotated examples to the model context. We investigate a contextual bandit version of in-context rei…
In-Context LearningIn-Context Reinforcement LearningReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI
Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of o…
Few-Shot Imitation LearningImitation LearningIn-Context LearningIn-Context Reinforcement Learning+1Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to the disadvantage of others has been ide…
In-Context Reinforcement Learningreinforcement-learningReinforcement Learning