World Models
Explore this paper's citation graph
Summary
This work explores building generative neural network models of popular reinforcement learning environments by using features extracted from the world model as inputs to an agent, and can train a very compact and simple policy that can solve the required task.
- Type
- preprint
- Published
- 2018-03-27
- Cited by
- 2,018
- References
- 176
- Access
- Open access
- OpenAlex
- https://openalex.org/W2795843265
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:4807711
Keywords
Hallucinating, Computer science, Reinforcement learning, Artificial intelligence, Task (project management)
References
- Dynamic reinforcement driven error propagation networks with application to game playing
- Acceleration and weight of extended bodies in the theory of relativity. [Doppler effect relation]
- Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
- Newtonian Universes and the Curvature of Space
- Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution
- Dynamics of Growth in a Finite World
- Playing Atari with Deep Reinforcement Learning
- Generating Sequences With Recurrent Neural Networks
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Curious model-building control systems
- Neural networks for control and system identification
- From Pixels to Torques: Policy Learning with Deep Dynamical Models
- Auto-Encoding Variational Bayes
- Could pressureless dark matter have pressure
- ON THE LOCAL DARK MATTER DENSITY
- Bound on the dark matter density in the Solar System from planetary motions
- Table of Integrals, Series, and Products
- Postulational approach to schwarzschild’s exterior solution with application to a class of interior solutions
- Effect of Sun and Planet-Bound Dark Matter on Planet and Satellite Dynamics in the Solar System
- Growth in a finite world - a comprehensive sensitivity analysis
Cited by
- Approximations of algorithmic and structural complexity validate cognitive-behavioral experimental results
- Chaotic spin precession in anisotropic universes and fermionic dark matter
- A DIFFERENTIABLE PHYSICS ENGINE FOR DEEP LEARNING IN ROBOTICS
- How dark matter came to matter
- Deep Learning for Video Game Playing
- Deep active inference
- State Representation Learning for Control: An Overview
- The evolution of modern cosmology as seen through a personal walk across six decades
- Unsupervised Video Object Segmentation for Deep Reinforcement Learning
- Learning Real-World Robot Policies by Dreaming
- Temporal Difference Variational Auto-Encoder
- A New Framework for Machine Intelligence: Concepts and Prototype
- Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
- RUDDER: Return Decomposition for Delayed Rewards
- Guided evolutionary strategies: escaping the curse of dimensionality in random search
- GONet++: Traversability Estimation via Dynamic Scene View Synthesis
- Learning to Drive in a Day
- Visual Reinforcement Learning with Imagined Goals
- Geometric Generalization Based Zero-Shot Learning Dataset Infinite World: Simple Yet Powerful
- A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
Related papers
- TC-VAE: Uncovering Out-of-Distribution Data Generative Factors
- Generative Model for Person Re-Identification: A Review
- Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet
- Are generative approaches to ZSAR a look in the right direction?
- A Comprehensive Review of the Latest Advancements in Large Generative AI Models
- Generating Realistic Blood-Cell Images using Cycle-Consistent Generative Adversial Networks
- Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay
- Deep Dexterous Grasping of Novel Objects from a Single View