About

The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.

( Image credit: Playing Atari with Deep Reinforcement Learning )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

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.

ATARI GAMES EFFICIENT EXPLORATION

On Catastrophic Interference in Atari 2600 Games

28 Feb 2020google-research/google-research

Our study provides a clear empirical link between catastrophic interference and sample efficiency in reinforcement learning.

ATARI GAMES

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

12 Jul 2020google-research/google-research

Model-based reinforcement learning (RL) is appealing because (i) it enables planning and thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables fast transfer to new reward functions.

MONTEZUMA'S REVENGE

Model-Based Reinforcement Learning for Atari

1 Mar 2019tensorflow/tensor2tensor

We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting.

ATARI GAMES VIDEO PREDICTION

Implicit Quantile Networks for Distributional Reinforcement Learning

ICML 2018 google/dopamine

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.

ATARI GAMES DISTRIBUTIONAL REINFORCEMENT LEARNING

Prioritized Experience Replay

18 Nov 2015google/dopamine

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past.

ATARI GAMES

RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning

24 Jun 2020deepmind/deepmind-research

We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.

ATARI GAMES DQN REPLAY DATASET MUJOCO GAMES

Asynchronous Methods for Deep Reinforcement Learning

4 Feb 2016tensorpack/tensorpack

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.

ATARI GAMES

Dueling Network Architectures for Deep Reinforcement Learning

20 Nov 2015tensorpack/tensorpack

In recent years there have been many successes of using deep representations in reinforcement learning.

ATARI GAMES

Deep Reinforcement Learning with Double Q-learning

22 Sep 2015tensorpack/tensorpack

The popular Q-learning algorithm is known to overestimate action values under certain conditions.

ATARI GAMES Q-LEARNING