71 citations · 160 across the 17 of their papers we have counts for
18 papers
Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Ruihan Zhao, Ufuk Topcu, Sandeep Chinchali +1
Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation and video games from hi…
Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning
Md Masudur Rahman, Yexiang Xue
This paper investigates the use of prior computation to estimate the value function to improve sample efficiency in on-policy policy gradient methods in reinforcement learning. Our…
Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation
Yifan Zhou, Shubham Sonawani, Mariano Phielipp +2
Language-conditioned policies allow robots to interpret and execute human instructions. Learning such policies requires a substantial investment with regards to time and compute re…
Group SELFIES: A Robust Fragment-Based Molecular String Representation
Austin Cheng, Andy Cai, Santiago Miret +3
We introduce Group SELFIES, a molecular string representation that leverages group tokens to represent functional groups or entire substructures while maintaining chemical robustne…
AnyMorph: Learning Transferable Polices By Inferring Agent Morphology
Brandon Trabucco, Mariano Phielipp, Glen Berseth
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 t…
Offline Policy Comparison with Confidence: Benchmarks and Baselines
Anurag Koul, Mariano Phielipp, Alan Fern
Decision makers often wish to use offline historical data to compare sequential-action policies at various world states. Importantly, computational tools should produce confidence…
Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design
Kourosh Hakhamaneshi, Marcel Nassar, Mariano Phielipp +2
Being able to predict the performance of circuits without running expensive simulations is a desired capability that can catalyze automated design. In this paper, we present a supe…
DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
Hassam Sheikh, Kizza Frisbee, Mariano Phielipp
Application of ensemble of neural networks is becoming an imminent tool for advancing the state-of-the-art in deep reinforcement learning algorithms. However, training these large…
Minimizing Communication while Maximizing Performance in Multi-Agent Reinforcement Learning
Varun Kumar Vijay, Hassam Sheikh, Somdeb Majumdar +1
Inter-agent communication can significantly increase performance in multi-agent tasks that require co-ordination to achieve a shared goal. Prior work has shown that it is possible…
Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization
Santiago Miret, Vui Seng Chua, Mattias Marder +3
Mixed-precision quantization is a powerful tool to enable memory and compute savings of neural network workloads by deploying different sets of bit-width precisions on separate com…
Instance based Generalization in Reinforcement Learning
Martin Bertran, Natalia Martinez, Mariano Phielipp +1
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.…
Language-Conditioned Imitation Learning for Robot Manipulation Tasks
Simon Stepputtis, Joseph Campbell, Mariano Phielipp +3
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., moti…
Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos
Ajay Kumar Tanwani, Pierre Sermanet, Andy Yan +3
Learning meaningful visual representations in an embedding space can facilitate generalization in downstream tasks such as action segmentation and imitation. In this paper, we lear…
Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation
Siyu Zhou, Mariano Phielipp, Jorge A. Sefair +2
In this paper, we propose SwarmNet -- a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner. Teste…
Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration
Simon Stepputtis, Joseph Campbell, Mariano Phielipp +2
In this work we propose a novel end-to-end imitation learning approach which combines natural language, vision, and motion information to produce an abstract representation of a ta…
On Training Flexible Robots using Deep Reinforcement Learning
Zach Dwiel, Madhavun Candadai, Mariano Phielipp
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 m…
Hierarchical Policy Learning is Sensitive to Goal Space Design
Zach Dwiel, Madhavun Candadai, Mariano Phielipp +1
Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transfera…
Goal-conditioned Imitation Learning
Yiming Ding, Carlos Florensa, Mariano Phielipp +1
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 partic…