Corpus ID: 235755271

RRL: Resnet as representation for Reinforcement Learning

  title={RRL: Resnet as representation for Reinforcement Learning},
  author={Rutav Shah and Vikash Kumar},
  • Rutav Shah, Vikash Kumar
  • Published 2021
  • Computer Science
  • ArXiv
The ability to autonomously learn behaviors via direct interactions in uninstrumented environments can lead to generalist robots capable of enhancing productivity or providing care in unstructured settings like homes. Such uninstrumented settings warrant operations only using the robot’s proprioceptive sensor such as onboard cameras, joint encoders, etc which can be challenging for policy learning owing to the high dimensionality and partial observability issues. We propose RRL: Resnet as… Expand
Learning to Navigate Sidewalks in Outdoor Environments
  • M. Sorokin, Jie Tan, C. Karen Liu, Sehoon Ha
  • Computer Science
  • ArXiv
  • 2021
A quadruped robot is developed that follows a route plan generated by public map services, while remaining on sidewalks and avoiding collisions with obstacles and pedestrians, in the city of Atlanta, USA. Expand
The Functional Correspondence Problem
Inspired by humans’ ability to generalize beyond semantic categories and infer functional affordances, the problem of functional correspondences is introduced and it is shown that the learned representation can generalize better on few-shot classification problem. Expand


Decoupling Representation Learning from Reinforcement Learning
A new unsupervised learning task, called Augmented Temporal Contrast (ATC), which trains a convolutional encoder to associate pairs of observations separated by a short time difference, under image augmentations and using a contrastive loss. Expand
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
A new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act, which significantly outperforms conventional baselines in zero-shot domain adaptation scenarios. Expand
Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders
An approach that automates state-space construction by learning a state representation directly from camera images by using a deep spatial autoencoder to acquire a set of feature points that describe the environment for the current task, such as the positions of objects. Expand
End-to-End Training of Deep Visuomotor Policies
This paper develops a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors, trained using a partially observed guided policy search method, with supervision provided by a simple trajectory-centric reinforcement learning method. Expand
Model-Based Reinforcement Learning for Atari
Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models, is described and a comparison of several model architectures is presented, including a novel architecture that yields the best results in the authors' setting. Expand
A Framework for Efficient Robotic Manipulation
It is shown that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels, such as reaching, picking, moving, pulling a large object, flipping a switch, and opening a drawer in just 15-50 minutes of real-world training time. Expand
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
QT-Opt is introduced, a scalable self-supervised vision-based reinforcement learning framework that can leverage over 580k real-world grasp attempts to train a deep neural network Q-function with over 1.2M parameters to perform closed-loop, real- world grasping that generalizes to 96% grasp success on unseen objects. Expand
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost
It is shown that contact-rich manipulation behavior with multi-fingered hands can be learned by directly training with model-free deep RL algorithms in the real world, with minimal additional assumption and without the aid of simulation, indicating that direct deep RL training in thereal world is a viable and practical alternative to simulation and model-based control. Expand
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
A new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) is developed that not only uses resources more efficiently in single-machine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. Expand
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
This paper proposes to represent a "fast" reinforcement learning algorithm as a recurrent neural network (RNN) and learn it from data, encoded in the weights of the RNN, which are learned slowly through a general-purpose ("slow") RL algorithm. Expand