Continuous Control Task

Continuous control tasks involve training agents to perform actions smoothly and continuously in dynamic environments, aiming to optimize performance metrics like reward maximization. Current research emphasizes robust and safe learning, focusing on techniques like model-based reinforcement learning (MBRL), hierarchical reinforcement learning (HRL), and ensemble methods to improve sample efficiency, generalization, and safety in complex scenarios. These advancements are crucial for deploying reinforcement learning in real-world applications, particularly in robotics, where safe and efficient control is paramount.

Papers

September 18, 2022

Evolutionary Deep Reinforcement Learning Using Elite Buffer: A Novel Approach Towards DRL Combined with EA in Continuous Control Tasks
Marzieh Sadat Esmaeeli, Hamed Malek
Reinforcement Learning Deep Reinforcement Learning Evolutionary Algorithm Evolutionary Computation Continuous Control Task Bentonite Buffer Ga DRL

July 29, 2022

Meta Reinforcement Learning with Successor Feature Based Context
Xu Han, Feng Wu
Meta Reinforcement Learning Continuous Control Task Successor Feature

July 5, 2022

Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization
Yuan Zhang, Jianhong Wang, Joschka Boedecker
Reinforcement Learning Regularization Model Robust Policy Robust Reinforcement Learning Continuous Control Task Real World Reinforcement Learning

June 12, 2022

Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Pratap Tokekar, Dinesh Manocha
Sparse Reward Sparse Reward Environment Continuous Control Task Heavy Tailed Policy

May 18, 2022

Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks
Ryan Sander, Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Sertac Karaman, Daniela Rus
Experience Replay Sample Efficiency Continuous Control Task Replay Buffer Policy Deep Reinforcement Learning Class Mixup

February 2, 2022

Imitation Learning by Estimating Expertise of Demonstrators
Mark Beliaev, Andy Shih, Stefano Ermon, Dorsa Sadigh, Ramtin Pedarsani
Imitation Learning Feature Imitation Noisy Demonstration Optimal Behavior Continuous Control Task Task Demonstration

December 27, 2021

Multiagent Model-based Credit Assignment for Continuous Control
Dongge Han, Chris Xiaoxuan Lu, Tomasz Michalak, Michael Wooldridge
Deep Reinforcement Learning Multi Agent Reinforcement Learning Continuous Control Continuous Control Task Decentralized Agent

December 10, 2021

Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots
Krishan Rana, Vibhavari Dasagi, Jesse Haviland, Ben Talbot, MIchael Milford, Niko Sünderhauf
Deep Reinforcement Learning Real Robot Continuous Control Task Uncertainty Aware Deployment Trained Policy Laboratory Robotics

November 30, 2021

Continuous Control With Ensemble Deep Deterministic Policy Gradients
Piotr Januszewski, Mateusz Olko, Michał Królikowski, Jakub Świątkowski, Marcin Andrychowicz, Łukasz Kuciński, Piotr Miłoś
Deep Reinforcement Learning Continuous Control Deep Deterministic Policy Gradient Continuous Control Task Ensemble Based Double Q Learning

Continuous Control Task

Papers

Evolutionary Deep Reinforcement Learning Using Elite Buffer: A Novel Approach Towards DRL Combined with EA in Continuous Control Tasks

Meta Reinforcement Learning with Successor Feature Based Context

Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization

Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies

Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks

Imitation Learning by Estimating Expertise of Demonstrators

Multiagent Model-based Credit Assignment for Continuous Control

Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots

Continuous Control With Ensemble Deep Deterministic Policy Gradients