We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards.
An agent solving tasks in a HANNA environment can leverage simulated human assistants, called ANNA (Automatic Natural Navigation Assistants), which, upon request, provide natural language and visual instructions to direct the agent towards the goals.
We took a custom camera rig to Igloo Cave at Mt.
A complex visual navigation task puts an agent in different situations which call for a diverse range of visual perception abilities.
In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator.
However, the application of deep RL to visual navigation with realistic environments is a challenging task.
Second, the latent space is modeled with a Mixture of Gaussians conditioned on the current observation and next best action.
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments.
In this paper we study the problem of learning to learn at both training and test time in the context of visual navigation.