State Representation Learning for Control: An Overview
Explore this paper's citation graph
Summary
This survey aims at covering the state-of-the-art on state representation learning in the most recent years by reviewing different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real).
- Type
- review
- Published
- 2018-02-12
- Cited by
- 382
- References
- 87
- Access
- Open access
- OpenAlex
- https://openalex.org/W2787666871
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3638188
Keywords
Representation (politics), Reinforcement learning, Computer science, Artificial intelligence, Curse of dimensionality
References
- Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives
- Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
- Learning state representations with robotic priors
- Introduction to Reinforcement Learning
- Algorithmic applications of low-distortion geometric embeddings
- A Survey of Dimension Reduction Techniques
- Multiscale structural similarity for image quality assessment
- Empowerment: a universal agent-centric measure of control
- Crossing the Reality Gap: a Short Introduction to the Transferability Approach
- Learning to Linearize Under Uncertainty
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- From Pixels to Torques: Policy Learning with Deep Dynamical Models
- Auto-Encoding Variational Bayes
- Slow feature analysis
- A Folded Neural Network Autoencoder for Dimensionality Reduction
- Extracting and composing robust features with denoising autoencoders
- A new embedding quality assessment method for manifold learning
- Robot Skill Learning: From Reinforcement Learning to Evolution Strategies
- Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations
- The Mario AI Benchmark and Competitions
Cited by
- Policy Search in Continuous Action Domains: an Overview
- Learning State Representations for Query Optimization with Deep Reinforcement Learning
- A Sensorimotor Perspective on Grounding the Semantic of Simple Visual Features
- Learning Representations of Spatial Displacement through Sensorimotor Prediction
- Learning Real-World Robot Policies by Dreaming
- A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
- Adaptive path-integral autoencoder: representation learning and planning for dynamical systems
- SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning
- Open-Ended Learning: A Conceptual Framework Based on Representational Redescription
- S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning
- Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
- Continual State Representation Learning for Reinforcement Learning using Generative Replay
- Learning Actionable Representations with Goal-Conditioned Policies
- Learning State Representations in Complex Systems with Multimodal Data
- Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
- Unsupervised Visuomotor Control through Distributional Planning Networks
- S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay
- The super‐learning hypothesis: Integrating learning processes across cortex, cerebellum and basal ganglia
- Evaluation of state representation methods in robot hand-eye coordination learning from demonstration
- Affordance Learning for End-to-End Visuomotor Robot Control
Related papers
- The Intrinsic Dimensionality of Data
- Encoding and Decoding Techniques for Distributed Data Storage Systems
- IEEE Access Special Section Editorial: Feature Representation and Learning Methods With Applications in Large-Scale Biological Sequence Analysis
- Learning Interpretable Disentangled Representations using Adversarial VAEs
- A Review of Disentangled Representation Learning for Remote Sensing Data
- Understanding-oriented visual representation learning
- Representation Learning for Fault Diagnosis with Contrastive Predictive Coding
- Representation Learning on Unstructured Data