Related papers: Comparing Task Simplifications to Learn Closed-Loo…
We present a method for reproducing complex multi-character interactions for physically simulated humanoid characters using deep reinforcement learning. Our method learns control policies for characters that imitate not only individual…
Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires…
This paper addresses the challenge of navigation in large, visually complex environments with sparse rewards. We propose a method that uses object-oriented macro actions grounded in a topological map, allowing a simple Deep Q-Network (DQN)…
This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor lead times, lost sales, correlated demand, and price matching. While this dynamic program has…
Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We…
The use of multi-camera views simultaneously has been shown to improve the generalization capabilities and performance of visual policies. However, the hardware cost and design constraints in real-world scenarios can potentially make it…
Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the…
Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must be bootstrapped using a good skill policy obtained from human demonstration. However, relying on human demonstration necessarily…
Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by…
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the…
We study the task of language-conditioned pick and place in clutter, where a robot should grasp a target object in open clutter and move it to a specified place. Some approaches learn end-to-end policies with features from vision foundation…
We propose a novel formulation of robotic pick and place as a deep reinforcement learning (RL) problem. Whereas most deep RL approaches to robotic manipulation frame the problem in terms of low level states and actions, we propose a more…
Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s)…
This paper proposes a detailed and extensive comparison of the Trust Region Policy Optimization and DeepQ-Network with Normalized Advantage Functions with respect to other state of the art algorithms, namely Deep Deterministic Policy…
Learning contact-rich, robotic manipulation skills is a challenging problem due to the high-dimensionality of the state and action space as well as uncertainty from noisy sensors and inaccurate motor control. To combat these factors and…
Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it…
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…
Robots equipped with rich sensing modalities (e.g., RGB-D cameras) performing long-horizon tasks motivate the need for policies that are highly memory-efficient. State-of-the-art approaches for controlling robots often use memory…
Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-based image classifier in front of a reinforcement learning…