# Meta Reinforcement Learning with Task Embedding and Shared Policy

arXiv: https://arxiv.org/abs/1905.06527 · HTML: https://mlsanity.com/paper/1905.06527/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2019.

## Built on by (most cited first, 15 of 15)

- [Leveraging Language for Accelerated Learning of Tool Manipulation](https://mlsanity.com/paper/2206.13074/) (2022)
- [Multi-Agent Policy Transfer via Task Relationship Modeling](https://mlsanity.com/paper/2203.04482/) (2022)
- [Meta-Reinforcement Learning in Broad and Non-Parametric Environments](https://mlsanity.com/paper/2108.03718/) (2021)
- [Meta-Reinforcement Learning by Tracking Task Non-stationarity](https://mlsanity.com/paper/2105.08834/) (2021)
- [Multi-Task Meta Learning: learn how to adapt to unseen tasks](https://mlsanity.com/paper/2210.06989/) (2022)
- [Neural Stochastic Dual Dynamic Programming](https://mlsanity.com/paper/2112.00874/) (2021)
- [MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation](https://mlsanity.com/paper/2510.16617/) (2025)
- [Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks](https://mlsanity.com/paper/2502.02834/) (2025)
- [TIMRL: A Novel Meta-Reinforcement Learning Framework for Non-Stationary and Multi-Task Environments](https://mlsanity.com/paper/2501.07146/) (2025)
- [Neural Operators for Multi-Task Control and Adaptation](https://mlsanity.com/paper/2604.03449/) (2026)
- [System-Agnostic Meta-Learning for MDP-based Dynamic Scheduling via Descriptive Policy](https://mlsanity.com/paper/2201.07051/) (2022)
- [Learning Embeddings for Sequential Tasks Using Population of Agents](https://mlsanity.com/paper/2306.03311/) (2023)
- [RL3: Boosting Meta Reinforcement Learning via RL inside RL2](https://mlsanity.com/paper/2306.15909/) (2023)
- [MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure](https://mlsanity.com/paper/2405.00902/) (2024)
- [Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning](https://mlsanity.com/paper/2506.19785/) (2025)

## Abstract (arXiv)

Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose to capture the shared information on the one hand and meta-learn how to quickly abstract the specific information about a task on the other hand. Methodologically, we train an SGD meta-learner to quickly optimize a task encoder for each task, which generates a task embedding based on past experience. Meanwhile, we learn a policy which is shared across all tasks and conditioned on task embeddings. Empirical results on four simulated tasks demonstrate that our method has better learning capacity on both training and novel tasks and attains up to 3 to 4 times higher returns compared to baselines.