# An Empowerment-based Solution to Robotic Manipulation Tasks with Sparse Rewards

arXiv: https://arxiv.org/abs/2010.07986 · HTML: https://mlsanity.com/paper/2010.07986/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Automatic Curricula via Expert Demonstrations](https://mlsanity.com/paper/2106.09159/) (2021)
- [FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions](https://mlsanity.com/paper/2504.10002/) (2025)
- [SuPLE: Robot Learning with Lyapunov Rewards](https://mlsanity.com/paper/2411.13613/) (2024)
- [Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2505.08630/) (2025)

## Abstract (arXiv)

In order to provide adaptive and user-friendly solutions to robotic manipulation, it is important that the agent can learn to accomplish tasks even if they are only provided with very sparse instruction signals. To address the issues reinforcement learning algorithms face when task rewards are sparse, this paper proposes an intrinsic motivation approach that can be easily integrated into any standard reinforcement learning algorithm and can allow robotic manipulators to learn useful manipulation skills with only sparse extrinsic rewards. Through integrating and balancing empowerment and curiosity, this approach shows superior performance compared to other state-of-the-art intrinsic exploration approaches during extensive empirical testing. Qualitative analysis also shows that when combined with diversity-driven intrinsic motivations, this approach can help manipulators learn a set of diverse skills which could potentially be applied to other more complicated manipulation tasks and accelerate their learning process.