Neural Embedding for Physical Manipulations
arXiv:1907.06143
Abstract
In common real-world robotic operations, action and state spaces can be vast and sometimes unknown, and observations are often relatively sparse. How do we learn the full topology of action and state spaces when given only few and sparse observations? Inspired by the properties of grid cells in mammalian brains, we build a generative model that enforces a normalized pairwise distance constraint between the latent space and output space to achieve data-efficient discovery of output spaces. This method achieves substantially better results than prior generative models, such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs). Prior models have the common issue of mode collapse and thus fail to explore the full topology of output space. We demonstrate the effectiveness of our model on various datasets both qualitatively and quantitatively.
References in corpus (18)
- Conditional Generative Adversarial Nets
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Spectral Normalization for Generative Adversarial Networks
- Tutorial on Variational Autoencoders
- Action-Conditional Video Prediction using Deep Networks in Atari Games
- Count-Based Exploration with Neural Density Models
- Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
- Unsupervised Learning for Physical Interaction through Video Prediction
- Unifying Count-Based Exploration and Intrinsic Motivation
- Learning and Transfer of Modulated Locomotor Controllers
- Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
- Hierarchical Implicit Models and Likelihood-Free Variational Inference
- Neural probabilistic motor primitives for humanoid control
- Variational Option Discovery Algorithms
- Latent Space Policies for Hierarchical Reinforcement Learning
- EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
- Interpretable Latent Spaces for Learning from Demonstration
- Empowerment for Continuous Agent-Environment Systems