Visual Episodic Memory-based Exploration
Not on the map. Why?
Abstract (arXiv)
In humans, intrinsic motivation is an important mechanism for open-ended cognitive development; in robots, it has been shown to be valuable for exploration. An important aspect of human cognitive development is textitepisodic memory which enables both the recollection of events from the past and the projection of subjective future. This paper explores the use of visual episodic memory as a source of intrinsic motivation for robotic exploration problems. Using a convolutional recurrent neural network autoencoder, the agent learns an efficient representation for spatiotemporal features such that accurate sequence prediction can only happen once spatiotemporal features have been learned. Structural similarity between ground truth and autoencoder generated images is used as an intrinsic motivation signal to guide exploration. Our proposed episodic memory model also implicitly accounts for the agent's actions, motivating the robot to seek new interactive experiences rather than just areas that are visually dissimilar. When guiding robotic exploration, our proposed method outperforms the Curiosity-driven Variational Autoencoder (CVAE) at finding dynamic anomalies.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 18 May 2024.
Builds on
16 of 35 references.
References · 16
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
- 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
- 2018Exploration by Random Network Distillationcited by 966
- 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
- 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
- 2018Large-Scale Study of Curiosity-Driven Learningcited by 277
- 2017Count-Based Exploration with Neural Density Modelscited by 255
- 2016Learning Temporal Regularity in Video Sequencescited by 254
- 2019Learning Exploration Policies for Navigationcited by 113
- 2018Episodic Curiosity through Reachabilitycited by 109
- 2017Abnormal Event Detection in Videos using Spatiotemporal Autoencodercited by 57
4 more
- 2020An Exploration of Embodied Visual Explorationcited by 56
- 2018Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learningcited by 14
- 2018Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Executioncited by 11
- 2018Sidekick Policy Learning for Active Visual Explorationcited by 11
Built on by
Not cited yet.