# Learning Context-aware Task Reasoning for Efficient Meta-reinforcement Learning

arXiv: https://arxiv.org/abs/2003.01373 · HTML: https://mlsanity.com/paper/2003.01373/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization](https://mlsanity.com/paper/2502.00691/) (2025)
- [Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies](https://mlsanity.com/paper/2310.16686/) (2023)
- [RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time](https://mlsanity.com/paper/2604.11626/) (2026)
- [ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning](https://mlsanity.com/paper/2206.05240/) (2022)
- [Meta-Reinforcement Learning in Broad and Non-Parametric Environments](https://mlsanity.com/paper/2108.03718/) (2021)
- [From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning](https://mlsanity.com/paper/2511.23031/) (2025)
- [Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning](https://mlsanity.com/paper/2306.07106/) (2023)
- [Behavior Self-Organization Supports Task Inference for Continual Robot Learning](https://mlsanity.com/paper/2107.04533/) (2021)
- [CogDoc: Towards Unified thinking in Documents](https://mlsanity.com/paper/2512.12658/) (2025)
- [TIMRL: A Novel Meta-Reinforcement Learning Framework for Non-Stationary and Multi-Task Environments](https://mlsanity.com/paper/2501.07146/) (2025)

## Abstract (arXiv)

Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies, they typically suffer from sampling inefficiency with on-policy RL algorithms or meta-overfitting with off-policy learning. In this work, we propose a novel meta-RL strategy to address those limitations. In particular, we decompose the meta-RL problem into three sub-tasks, task-exploration, task-inference and task-fulfillment, instantiated with two deep network agents and a task encoder. During meta-training, our method learns a task-conditioned actor network for task-fulfillment, an explorer network with a self-supervised reward shaping that encourages task-informative experiences in task-exploration, and a context-aware graph-based task encoder for task inference. We validate our approach with extensive experiments on several public benchmarks and the results show that our algorithm effectively performs exploration for task inference, improves sample efficiency during both training and testing, and mitigates the meta-overfitting problem.