Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds

• URL: http://arxiv.org/abs/2502.02869v2
• Date: Tue, 01 Jul 2025 03:07:05 GMT
• Title: Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
• Authors: Fan Wang, Pengtao Shao, Yiming Zhang, Bo Yu, Shaoshan Liu, Ning Ding, Yang Cao, Yu Kang, Haifeng Wang,
• Abstract summary: In-Context Reinforcement Learning (ICRL) enables agents to learn automatically and on-the-fly from their interactive experiences.<n>We propose the procedurally generated Markov Decision Processes, named AnyMDP.<n>Our results demonstrate that, with a sufficiently large scale of AnyMDP tasks, the proposed model can generalize to tasks that were not considered in the training set.
• Score: 35.652208216209985
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-Context Reinforcement Learning (ICRL) enables agents to learn automatically and on-the-fly from their interactive experiences. However, a major challenge in scaling up ICRL is the lack of scalable task collections. To address this, we propose the procedurally generated tabular Markov Decision Processes, named AnyMDP. Through a carefully designed randomization process, AnyMDP is capable of generating high-quality tasks on a large scale while maintaining relatively low structural biases. To facilitate efficient meta-training at scale, we further introduce step-wise supervision and induce prior information in the ICRL framework.Our results demonstrate that, with a sufficiently large scale of AnyMDP tasks, the proposed model can generalize to tasks that were not considered in the training set. The scalable task set provided by AnyMDP also enables a more thorough empirical investigation of the relationship between data distribution and ICRL performance. We further show that the generalization of ICRL potentially comes at the cost of increased task diversity and longer adaptation periods. This finding carries critical implications for scaling robust ICRL capabilities, highlighting the necessity of diverse and extensive task design, and prioritizing asymptotic performance over few-shot adaptation.

Related papers

• Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning [1.6114012813668932]
  Small language models (LLMs) struggle to develop a generic Theory of Mind (ToM) capability.<n> prolonged RL training leads to models hacking'' the statistical patterns of the training datasets.<n>This suggests the learned behavior is a form of narrow overfitting rather than the acquisition of a true, abstract ToM capability.
  arXiv  Detail & Related papers  (2025-07-21T16:47:59Z)
• Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards [50.21528417884747]
  We introduce Omni-Thinker, a unified reinforcement learning framework that enhances large language models (LLMs) performance across diverse tasks.<n>Our approach enables consistent optimization across task types and scales RL-based training to subjective domains.<n> Experimental results across four domains reveal that curriculum learning improves performance by 5.2% over joint training and 9.1% over model merging.
  arXiv  Detail & Related papers  (2025-07-20T01:50:16Z)
• Causal-Paced Deep Reinforcement Learning [4.728991543521559]
  Causal-Paced Deep Reinforcement Learning (CP-DRL) is a curriculum learning framework aware of SCM differences between tasks based on interaction data approximation.<n> Empirically, CP-DRL outperforms existing curriculum methods on the Point Mass benchmark.
  arXiv  Detail & Related papers  (2025-06-24T20:15:01Z)
• Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study [11.452011929848844]
  This study proposes a novel meta-surrogate framework to assist many-task optimization.<n>We formulate a unified framework for many-task fitness prediction, by defining a universal model with metadata to fit a group of problems.<n>Our framework supports dual-level knowledge transfer -- at both the surrogate and individual levels -- enhancing optimization efficiency and robustness.
  arXiv  Detail & Related papers  (2025-03-11T11:13:11Z)
• Vintix: Action Model via In-Context Reinforcement Learning [72.65703565352769]
  We present the first steps toward scaling ICRL by introducing a fixed, cross-domain model capable of learning behaviors through in-context reinforcement learning.<n>Our results demonstrate that Algorithm Distillation, a framework designed to facilitate ICRL, offers a compelling and competitive alternative to expert distillation to construct versatile action models.
  arXiv  Detail & Related papers  (2025-01-31T18:57:08Z)
• Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning [62.984693936073974]
  Value-based reinforcement learning can learn effective policies for a wide range of multi-turn problems. Current value-based RL methods have proven particularly challenging to scale to the setting of large language models. We propose a novel offline RL algorithm that addresses these drawbacks, casting Q-learning as a modified supervised fine-tuning problem.
  arXiv  Detail & Related papers  (2024-11-07T21:36:52Z)
• On the Modeling Capabilities of Large Language Models for Sequential Decision Making [52.128546842746246]
  Large pretrained models are showing increasingly better performance in reasoning and planning tasks. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly. In environments with unfamiliar dynamics, we explore how fine-tuning LLMs with synthetic data can significantly improve their reward modeling capabilities.
  arXiv  Detail & Related papers  (2024-10-08T03:12:57Z)
• Benchmarking General-Purpose In-Context Learning [19.40952728849431]
  In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly. In this paper, we study extending ICL to address a broader range of tasks with an extended learning horizon and higher improvement potential. We introduce two benchmarks specifically crafted to train and evaluate GPICL functionalities.
  arXiv  Detail & Related papers  (2024-05-27T14:50:42Z)
• Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks [53.44714413181162]
  This paper shows that when an agent is trained on a sufficiently diverse set of tasks, a generic policy-sharing algorithm with myopic exploration design can be sample-efficient. To the best of our knowledge, this is the first theoretical demonstration of the "exploration benefits" of MTRL.
  arXiv  Detail & Related papers  (2024-03-03T22:57:44Z)
• M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation [0.7564784873669823]
  We propose Multimodal Contrastive Unsupervised Reinforcement Learning (M2CURL) Our approach employs a novel multimodal self-supervised learning technique that learns efficient representations and contributes to faster convergence of RL algorithms. We evaluate M2CURL on the Tactile Gym 2 simulator and we show that it significantly enhances the learning efficiency in different manipulation tasks.
  arXiv  Detail & Related papers  (2024-01-30T14:09:35Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes [56.714690083118406]
  In multi-task reinforcement learning (RL) under Markov decision processes (MDPs), the presence of shared latent structures has been shown to yield significant benefits to the sample efficiency compared to single-task RL. We investigate whether such a benefit can extend to more general sequential decision making problems, such as partially observable MDPs (POMDPs) and more general predictive state representations (PSRs) We propose a provably efficient algorithm UMT-PSR for finding near-optimal policies for all PSRs, and demonstrate that the advantage of multi-task learning manifests if the joint model class of PSR
  arXiv  Detail & Related papers  (2023-10-20T14:50:28Z)
• Model-Based Reinforcement Learning with Multi-Task Offline Pretraining [59.82457030180094]
  We present a model-based RL method that learns to transfer potentially useful dynamics and action demonstrations from offline data to a novel task. The main idea is to use the world models not only as simulators for behavior learning but also as tools to measure the task relevance. We demonstrate the advantages of our approach compared with the state-of-the-art methods in Meta-World and DeepMind Control Suite.
  arXiv  Detail & Related papers  (2023-06-06T02:24:41Z)
• Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning [23.45043290237396]
  MoSS is a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior in terms of performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization.
  arXiv  Detail & Related papers  (2023-04-29T15:46:19Z)
• Meta Reinforcement Learning with Successor Feature Based Context [51.35452583759734]
  We propose a novel meta-RL approach that achieves competitive performance comparing to existing meta-RL algorithms. Our method does not only learn high-quality policies for multiple tasks simultaneously but also can quickly adapt to new tasks with a small amount of training.
  arXiv  Detail & Related papers  (2022-07-29T14:52:47Z)
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning [11.076005074172516]
  reinforcement learning algorithms can easily encounter catastrophic forgetting or interference when faced with lifelong streaming information. We propose a scalable lifelong RL method that dynamically expands the network capacity to accommodate new knowledge. We show that our method successfully facilitates scalable lifelong RL and outperforms relevant existing methods.
  arXiv  Detail & Related papers  (2022-05-22T09:48:41Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents [0.0]
  In this paper, we introduce a meta-learning scheme that shifts the objective of learning to solve a task into the objective of learning to learn to solve a task (or a set of tasks) Our model, named REIN-2, is a meta-learning scheme formulated within the RL framework, the goal of which is to develop a meta-RL agent that learns how to produce other RL agents. Compared to traditional state-of-the-art Deep RL algorithms, experimental results show remarkable performance of our model in popular OpenAI Gym environments.
  arXiv  Detail & Related papers  (2021-10-11T10:13:49Z)
• Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning [114.07623388322048]
  We discuss how the standard goal-conditioned RL (GCRL) is encapsulated by the objective variational empowerment. Our work lays a novel foundation from which to evaluate, analyze, and develop representation learning techniques in goal-based RL.
  arXiv  Detail & Related papers  (2021-06-02T18:12:26Z)
• Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning [83.66080019570461]
  We propose two environment-agnostic, algorithm-agnostic quantitative metrics for task difficulty. We show that these metrics have higher correlations with normalized task solvability scores than a variety of alternatives. These metrics can also be used for fast and compute-efficient optimizations of key design parameters.
  arXiv  Detail & Related papers  (2021-03-23T17:49:50Z)
• FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization [10.243908145832394]
  We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks. This problem is still not fully understood, for which two major challenges need to be addressed. We provide analysis and insight showing that some simple design choices can yield substantial improvements over recent approaches.
  arXiv  Detail & Related papers  (2020-10-02T17:13:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.