• Publications
  • Influence
Lyapunov-based Safe Policy Optimization for Continuous Control
TLDR
Safe policy optimization algorithms based on a Lyapunov approach to solve continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations are presented.
Learning Navigation Behaviors End-to-End With AutoRL
TLDR
Empirical evaluations show that AutoRL policies do not suffer from the catastrophic forgetfulness that plagues many other deep reinforcement learning algorithms, generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks.
Automated aerial suspended cargo delivery through reinforcement learning
TLDR
This article presents a solution to a challenging, and vital problem of planning a constraint-balancing task for an inherently unstable non-linear system in the presence of obstacles and defines formal conditions for a class of robotics problems where learning can occur in a simplified problem space and successfully transfer to a broader problem space.
PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-Based Planning
TLDR
This work presents PRM-RL, a hierarchical method for long-range navigation task completion that combines sampling-based path planning with reinforcement learning (RL), and evaluates it on two navigation tasks with non-trivial robot dynamics.
Long-Range Indoor Navigation With PRM-RL
TLDR
This article uses probabilistic roadmaps (PRMs) as the sampling-based planner, and AutoRL as the RL method in the indoor navigation context, and shows that PRM-RL with AutoRL is more successful than several baselines, is robust to noise, and can guide robots over hundreds of meters in the face of noise and obstacles in both simulation and on robots.
MAVBench: Micro Aerial Vehicle Benchmarking
TLDR
The MAVBench framework is introduced, which consists of a closed-loop simulator and an end-to-end application benchmark suite, and a benchmark suite consisting of a variety of MAV applications designed to enable computer architects to perform characterization and develop future aerial computing systems.
FollowNet: Robot Navigation by Following Natural Language Directions with Deep Reinforcement Learning
TLDR
It is shown that the FollowNet agent learns to execute previously unseen instructions described with a similar vocabulary, and successfully navigates along paths not encountered during training, and shows 30% improvement over a baseline model without the attention mechanism.
Quantized Reinforcement Learning (QUARL)
TLDR
This first comprehensive empirical study that quantifies the effects of quantization on various deep reinforcement learning policies with the intent to reduce their computational resource demands and demonstrates real-world applications ofquantization for reinforcement learning.
Learning to Navigate the Web
TLDR
DQN, deep reinforcement learning agent, with Q-value function approximated with a novel QWeb neural network architecture is trained with the ability of the agent to generalize to new instructions on World of Bits benchmark, on forms with up to 100 elements, supporting 14 million possible instructions.
Learning swing-free trajectories for UAVs with a suspended load
TLDR
This paper presents a motion planning method for generating trajectories with minimal residual oscillations (swing-free) for rotorcraft carrying a suspended loads using a finite-sampling, batch reinforcement learning algorithm.
...
1
2
3
4
5
...