12 accepted papers
Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation, and video games from high-dimensional pixel observations. However, RL usually relies on domain-specific reward functions for sufficient learni…
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs. However, RL requires careful structuring of the search space and algorithm design to be effective in this challenge. Through extensive experiments, we explore how diffe…
We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations in the context of realistic robot tasks. Recent offline model-free approaches successfully use online fine-tuning to either improve the performance of the agent over the…
The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology. Recent work aims to eliminate the re-training of policies by investigating whether a morphology-agnostic policy, trained on a diverse set of agents wit…
The application of an ensemble of neural networks is becoming an imminent tool for advancing state-of-the-art deep reinforcement learning algorithms. However, training these large numbers of neural networks in the ensemble has an exceedingly high computation cost which may become a hindrance in trai…
Modern deep reinforcement learning (DRL) has been successful in solving a range of challenging sequential decision-making problems. Most of these algorithms use an ensemble of neural networks as their backbone structure and benefit from the diversity among the neural networks to achieve optimal resu…
Language-conditioned policies allow robots to interpret and execute human instructions. Learning such policies requires a substantial investment with regards to time and compute resources. Still, the resulting controllers are highly device-specific and cannot easily be transferred to a robot with di…
Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of the challenges of modern machine learning. Towards this goal…
Imitation learning is a popular approach for teaching motor skills to robots. However, most approaches focus on extracting policy parameters from execution traces alone (i.e., motion trajectories and perceptual data). No adequate communication channel exists between the human expert and the robot to…
Learning meaningful visual representations in an embedding space can facilitate generalization in downstream tasks such as action segmentation and imitation. In this paper, we learn a motion-centric representation of surgical video demonstrations by grouping them into action segments/subgoals/option…
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where detecting whether the desired configuration is reached might requ…
The use of robotics in controlled environments has flourished over the last several decades and training robots to perform tasks using control strategies developed from dynamical models of their hardware have proven very effective. However, in many real-world settings, the uncertainties of the envir…