-
Self-Organizing Maps as a Storage and Transfer Mechanism in Reinforcement Learning
The idea of reusing information from previously learned tasks (source ta...
read it
-
Lessons from reinforcement learning for biological representations of space
Neuroscientists postulate 3D representations in the brain in a variety o...
read it
-
Unsupervised Domain Adaptation for Visual Navigation
Advances in visual navigation methods have led to intelligent embodied n...
read it
-
Embodied Multimodal Multitask Learning
Recent efforts on training visual navigation agents conditioned on langu...
read it
-
Learning View and Target Invariant Visual Servoing for Navigation
The advances in deep reinforcement learning recently revived interest in...
read it
-
From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)
Visual Indoor Navigation (VIN) task has drawn increasing attentions from...
read it
-
Examining Representational Similarity in ConvNets and the Primate Visual Cortex
We compare several ConvNets with different depth and regularization tech...
read it
Analyzing Visual Representations in Embodied Navigation Tasks
Recent advances in deep reinforcement learning require a large amount of training data and generally result in representations that are often over specialized to the target task. In this work, we present a methodology to study the underlying potential causes for this specialization. We use the recently proposed projection weighted Canonical Correlation Analysis (PWCCA) to measure the similarity of visual representations learned in the same environment by performing different tasks. We then leverage our proposed methodology to examine the task dependence of visual representations learned on related but distinct embodied navigation tasks. Surprisingly, we find that slight differences in task have no measurable effect on the visual representation for both SqueezeNet and ResNet architectures. We then empirically demonstrate that visual representations learned on one task can be effectively transferred to a different task.
READ FULL TEXT
Comments
There are no comments yet.