Multi-Task & Transfer Reinforcement Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Reusing knowledge across tasks is essential for generalist agents. This list covers multi-task objectives, transfer bounds, and modular sharing.

Multi-Task & Transfer Reinforcement Learning: 10 key papers

1. Distral: Robust Multitask Reinforcement Learning
   Teh et al. arXiv 2017.
2. Gradient Surgery for Multi-Task Learning
   Yu et al. arXiv 2020.
3. Multi-task Deep Reinforcement Learning with PopArt
   Hessel et al. arXiv 2018.
4. Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
   Yu et al. arXiv 2019.
5. Multi-Task Reinforcement Learning with Soft Modularization
   Yang et al. arXiv 2020.
6. IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
   Espeholt et al. arXiv 2018.
7. Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
   Parisotto et al. arXiv 2015.
8. Policy Distillation
   Rusu et al. arXiv 2015.
9. Conflict-Averse Gradient Descent for Multi-task Learning
   Liu et al. arXiv 2021.
10. Multi-Task Learning as Multi-Objective Optimization
    Sener and Koltun. arXiv 2018.

Related reading lists

• Zero-Shot RL & Generalization
• Knowledge Distillation
• Policy Gradient Methods
• Off-Policy Evaluation & Offline Evaluation
• In-Context RL & Prompting
• Representation Learning for RL
• Meta-Reinforcement Learning
• Hyperparameter Optimization & AutoML