# ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations

arXiv: https://arxiv.org/abs/1910.12154 · HTML: https://mlsanity.com/paper/1910.12154/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 26 Oct 2019.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards](https://mlsanity.com/paper/1707.08817/) (2017)
- [Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents](https://mlsanity.com/paper/1709.06009/) (2017)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [A Deeper Look at Experience Replay](https://mlsanity.com/paper/1712.01275/) (2017)
- [Kickstarting Deep Reinforcement Learning](https://mlsanity.com/paper/1803.03835/) (2018)
- [Learning Montezuma's Revenge from a Single Demonstration](https://mlsanity.com/paper/1812.03381/) (2018)
- [Diagnosing Bottlenecks in Deep Q-learning Algorithms](https://mlsanity.com/paper/1902.10250/) (2019)
- [Making Efficient Use of Demonstrations to Solve Hard Exploration Problems](https://mlsanity.com/paper/1909.01387/) (2019)
- [Observe and Look Further: Achieving Consistent Performance on Atari](https://mlsanity.com/paper/1805.11593/) (2018)
- [An Optimistic Perspective on Offline Reinforcement Learning](https://mlsanity.com/paper/1907.04543/) (2019)
- [A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning](https://mlsanity.com/paper/1810.01531/) (2018)

## Built on by (most cited first, 5 of 5)

- [Shared Autonomy for Proximal Teaching](https://mlsanity.com/paper/2502.19899/) (2025)
- [Towards Teachable Autotelic Agents](https://mlsanity.com/paper/2105.11977/) (2021)
- [GLIDE-RL: Grounded Language Instruction through DEmonstration in RL](https://mlsanity.com/paper/2401.02991/) (2024)
- [DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning](https://mlsanity.com/paper/2109.07380/) (2021)
- [Autonomous Curriculum Design via Relative Entropy Based Task Modifications](https://mlsanity.com/paper/2502.21166/) (2025)

## Abstract (arXiv)

Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning. When providing expert demonstrations to human students, we know that the demonstrations must fall within a particular range of difficulties called the "Zone of Proximal Development (ZPD)". If they are too easy the student learns nothing, but if they are too difficult the student is unable to follow along. This raises the question: Given a set of potential demonstrators, which among them is best suited for teaching any particular learner? Prior work, such as the popular Deep Q-learning from Demonstrations (DQfD) algorithm has generally focused on single demonstrators. In this work we consider the problem of choosing among multiple demonstrators of varying skill levels. Our results align with intuition from human learners: it is not always the best policy to draw demonstrations from the best performing demonstrator (in terms of reward). We show that careful selection of teaching strategies can result in sample efficiency gains in the learner's environment across nine Atari games