Continuous Control
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
Greatest papers with code
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
ICLR 2019
• tensorflow/models
• 
We study the problem of representation learning in goal-conditioned hierarchical reinforcement learning.
CONTINUOUS CONTROL HIERARCHICAL REINFORCEMENT LEARNING REPRESENTATION LEARNING
Parameter Space Noise for Exploration
ICLR 2018
• tensorflow/models
•
Combining parameter noise with traditional RL methods allows to combine the best of both worlds.
Benchmarking Deep Reinforcement Learning for Continuous Control
• openai/rllab
•
Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
ICML 2018
• facebookresearch/Horizon
• 
A platform for Applied Reinforcement Learning (Applied RL)
Continuous control with deep reinforcement learning
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain.
DeepMind Control Suite
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.
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.
Sample Efficient Actor-Critic with Experience Replay
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.
Learning Latent Dynamics for Planning from Pixels
Planning has been very successful for control tasks with known environment dynamics.
Simple random search provides a competitive approach to reinforcement learning
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.