How to train your robot with deep reinforcement learning: lessons we have learned
Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …
acquiring complex behaviors from low-level sensor observations. Although a large portion of …
A survey on policy search algorithms for learning robot controllers in a handful of trials
K Chatzilygeroudis, V Vassiliades… - IEEE Transactions …, 2019 - ieeexplore.ieee.org
Most policy search (PS) algorithms require thousands of training episodes to find an
effective policy, which is often infeasible with a physical robot. This survey article focuses on …
effective policy, which is often infeasible with a physical robot. This survey article focuses on …
Solar: Deep structured representations for model-based reinforcement learning
Abstract Model-based reinforcement learning (RL) has proven to be a data efficient
approach for learning control tasks but is difficult to utilize in domains with complex …
approach for learning control tasks but is difficult to utilize in domains with complex …
Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task
S James, AJ Davison, E Johns - Conference on Robot …, 2017 - proceedings.mlr.press
End-to-end control for robot manipulation and grasping is emerging as an attractive
alternative to traditional pipelined approaches. However, end-to-end methods tend to either …
alternative to traditional pipelined approaches. However, end-to-end methods tend to either …
Reset-free reinforcement learning via multi-task learning: Learning dexterous manipulation behaviors without human intervention
Reinforcement Learning (RL) algorithms can in principle acquire complex robotic skills by
learning from large amounts of data in the real world, collected via trial and error. However …
learning from large amounts of data in the real world, collected via trial and error. However …
Combining model-based and model-free updates for trajectory-centric reinforcement learning
Reinforcement learning algorithms for real-world robotic applications must be able to handle
complex, unknown dynamical systems while maintaining data-efficient learning. These …
complex, unknown dynamical systems while maintaining data-efficient learning. These …
[HTML][HTML] Reset-free trial-and-error learning for robot damage recovery
The high probability of hardware failures prevents many advanced robots (eg, legged
robots) from being confidently deployed in real-world situations (eg, post-disaster rescue) …
robots) from being confidently deployed in real-world situations (eg, post-disaster rescue) …
Constrained cross-entropy method for safe reinforcement learning
We study a safe reinforcement learning problem in which the constraints are defined as the
expected cost over finite-length trajectories. We propose a constrained cross-entropy-based …
expected cost over finite-length trajectories. We propose a constrained cross-entropy-based …
Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system
Reinforcement learning has emerged as a promising methodology for training robot
controllers. However, most results have been limited to simulation due to the need for a …
controllers. However, most results have been limited to simulation due to the need for a …
Dual policy iteration
Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated
impressive practical performance (eg, ExIt from [1], AlphaGo-Zero from [2]). This new family …
impressive practical performance (eg, ExIt from [1], AlphaGo-Zero from [2]). This new family …