# Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning

arXiv: https://arxiv.org/abs/1810.11388 · HTML: https://mlsanity.com/paper/1810.11388/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2018.

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

- [Survey on reinforcement learning for language processing](https://mlsanity.com/paper/2104.05565/) (2021)
- [Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning](https://mlsanity.com/paper/2305.02054/) (2023)
- [Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review](https://mlsanity.com/paper/2301.10067/) (2023)
- [Sample-efficient Real-time Planning with Curiosity Cross-Entropy Method and Contrastive Learning](https://mlsanity.com/paper/2303.03787/) (2023)
- [Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks](https://mlsanity.com/paper/2407.21338/) (2024)

## Abstract (arXiv)

In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive the hidden representation of a deep convolutional autoencoder which is trained to reconstruct the visual input, while the centre-most hidden representation is also optimized to estimate the state value. Separately, an ensemble of predictive world models generates, based on its learning progress, an intrinsic reward signal which is combined with the extrinsic reward to guide the exploration of the actor-critic learner. Our approach is more data-efficient and inherently more stable than the existing actor-critic methods for continuous control from pixel data. We evaluate our algorithm for the task of learning robotic reaching and grasping skills on a realistic physics simulator and on a humanoid robot. The results show that the control policies learned with our approach can achieve better performance than the compared state-of-the-art and baseline algorithms in both dense-reward and challenging sparse-reward settings.