Browse > Playing Games > Continuous Control

Continuous Control

63 papers with code · Playing Games

State-of-the-art leaderboards

Greatest papers with code

Parameter Space Noise for Exploration

ICLR 2018 tensorflow/models

Combining parameter noise with traditional RL methods allows to combine the best of both worlds.

CONTINUOUS CONTROL

Benchmarking Deep Reinforcement Learning for Continuous Control

22 Apr 2016openai/rllab

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.

ATARI GAMES CONTINUOUS CONTROL

Continuous control with deep reinforcement learning

9 Sep 2015facebookresearch/Horizon

We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain.

CONTINUOUS CONTROL Q-LEARNING

DeepMind Control Suite

2 Jan 2018deepmind/dm_control

The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents.

CONTINUOUS CONTROL

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

NeurIPS 2017 hill-a/stable-baselines

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature.

ATARI GAMES CONTINUOUS CONTROL

Sample Efficient Actor-Critic with Experience Replay

3 Nov 2016hill-a/stable-baselines

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems.

CONTINUOUS CONTROL

Learning Latent Dynamics for Planning from Pixels

12 Nov 2018google-research/planet

Planning has been very successful for control tasks with known environment dynamics.

CONTINUOUS CONTROL MOTION PLANNING

Simple random search provides a competitive approach to reinforcement learning

19 Mar 2018modestyachts/ARS

A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions.

CONTINUOUS CONTROL