Atari Games
The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Greatest papers with code
Deep Exploration via Bootstrapped DQN
NeurIPS 2016
• tensorflow/models
• 
Efficient exploration in complex environments remains a major challenge for reinforcement learning.
SOTA for Atari Games on Atari 2600 Breakout
Implicit Quantile Networks for Distributional Reinforcement Learning
In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN.
SOTA for Atari Games on Atari 2600 Beam Rider
Prioritized Experience Replay
• google/dopamine
•
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past.
Asynchronous Methods for Deep Reinforcement Learning
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.
SOTA for Atari Games on Atari 2600 Asteroids
Dueling Network Architectures for Deep Reinforcement Learning
In recent years there have been many successes of using deep representations in reinforcement learning.
SOTA for Atari Games on Atari 2600 Bank Heist
Playing Atari with Deep Reinforcement Learning
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.
SOTA for Atari Games on Atari 2600 Pong
Increasing the Action Gap: New Operators for Reinforcement Learning
Extending the idea of a locally consistent operator, we then derive sufficient conditions for an operator to preserve optimality, leading to a family of operators which includes our consistent Bellman operator.
Benchmarking Deep Reinforcement Learning for Continuous Control
• rllab/rllab
•
Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
NeurIPS 2017
• facebookresearch/ELF
• 
In addition, our platform is flexible in terms of environment-agent communication topologies, choices of RL methods, changes in game parameters, and can host existing C/C++-based game environments like Arcade Learning Environment.
A Distributional Perspective on Reinforcement Learning
ICML 2017
• NervanaSystems/coach
•
We obtain both state-of-the-art results and anecdotal evidence demonstrating the importance of the value distribution in approximate reinforcement learning.
SOTA for Atari Games on Atari 2600 Asterix