# Fill in the Blanks: Accelerating Q-Learning with a Handful of Demonstrations in Sparse Reward Settings

arXiv: https://arxiv.org/abs/2510.24432 · HTML: https://mlsanity.com/paper/2510.24432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 19 of 19)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.04717/) (2016)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [Stop Regressing: Training Value Functions via Classification for Scalable Deep RL](https://mlsanity.com/paper/2403.03950/) (2024)
- [Munchausen Reinforcement Learning](https://mlsanity.com/paper/2007.14430/) (2020)
- [Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation](https://mlsanity.com/paper/2010.01114/) (2020)
- [Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning](https://mlsanity.com/paper/2306.03186/) (2023)
- [SR-Reward: Taking The Path More Traveled](https://mlsanity.com/paper/2501.02330/) (2025)

## Abstract (arXiv)

Reinforcement learning (RL) in sparse-reward environments remains a significant challenge due to the lack of informative feedback. We propose a simple yet effective method that uses a small number of successful demonstrations to initialize the value function of an RL agent. By precomputing value estimates from offline demonstrations and using them as targets for early learning, our approach provides the agent with a useful prior over promising actions. The agent then refines these estimates through standard online interaction. This hybrid offline-to-online paradigm significantly reduces the exploration burden and improves sample efficiency in sparse-reward settings. Experiments on benchmark tasks demonstrate that our method accelerates convergence and outperforms standard baselines, even with minimal or suboptimal demonstration data.