Search Results for author:
Found 21 papers, 7 papers with code
MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning
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.
Searching for High-Value Molecules Using Reinforcement Learning and Transformers
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs.
Group SELFIES: A Robust Fragment-Based Molecular String Representation
We introduce Group SELFIES, a molecular string representation that leverages group tokens to represent functional groups or entire substructures while maintaining chemical robustness guarantees.
AnyMorph: Learning Transferable Polices By Inferring Agent Morphology
Ours is the first reinforcement learning algorithm that can train a policy to generalize to new agent morphologies without requiring a description of the agent's morphology in advance.
Offline Policy Comparison with Confidence: Benchmarks and Baselines
Decision makers often wish to use offline historical data to compare sequential-action policies at various world states.
Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design
We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties with up to 10x more sample efficiency compared to a randomly initialized model.
DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning
Application of ensemble of neural networks is becoming an imminent tool for advancing the state-of-the-art in deep reinforcement learning algorithms.
Maximizing Ensemble Diversity in Deep Reinforcement Learning
In this paper, we describe Maximize Ensemble Diversity in Reinforcement Learning (MED-RL), a set of regularization methods inspired from the economics and consensus optimization to improve diversity in the ensemble-based deep reinforcement learning methods by encouraging inequality between the networks during training.
Minimizing Communication while Maximizing Performance in Multi-Agent Reinforcement Learning
With these techniques, we show that we can reduce communication by 75% with no loss of performance.
Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization
In this work, we present a flexible and scalable framework for automated mixed-precision quantization that concurrently optimizes task performance, memory compression, and compute savings through multi-objective evolutionary computing.
ReaPER: Improving Sample Efficiency in Model-Based Latent Imagination
Deep Reinforcement Learning (DRL) can distill behavioural policies from sensory input that solve complex tasks, however, the policies tend to be task-specific and sample inefficient, requiring a large number of interactions with the environment that may be costly or impractical for many real world applications.
Instance-based Generalization in Reinforcement Learning
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.
Instance based Generalization in Reinforcement Learning
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
Imitation learning is a popular approach for teaching motor skills to robots.
Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos
We demonstrate the use of this representation to imitate surgical suturing motions from publicly available videos of the JIGSAWS dataset.
Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation
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.
Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration
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 task, which in turn is used to synthesize specific motion controllers at run-time.
Imitation Learning of Robot Policies using Language, Vision and Motion
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 task, which in turn can be used to synthesize specific motion controllers at run-time.
On Training Flexible Robots using Deep Reinforcement Learning
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.
Goal-conditioned Imitation Learning
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.
Hierarchical Policy Learning is Sensitive to Goal Space Design
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 transferability of sub-policies to tasks outside the training distribution.
