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

Latest papers without code

Combining Off and On-Policy Training in Model-Based Reinforcement Learning

24 Feb 2021

Recently, MuZero demonstrated that it is possible to master both Atari games and board games by directly learning a model of the environment, which is then used with MCTS to decide what move to play in each position.

ATARI GAMES BOARD GAMES

Return-Based Contrastive Representation Learning for Reinforcement Learning

ICLR 2021

Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL).

ATARI GAMES REPRESENTATION LEARNING

Q-Value Weighted Regression: Reinforcement Learning with Limited Data

12 Feb 2021

QWR is an extension of Advantage Weighted Regression (AWR), an off-policy actor-critic algorithm that performs very well on continuous control tasks, also in the offline setting, but has low sample efficiency and struggles with high-dimensional observation spaces.

ATARI GAMES CONTINUOUS CONTROL OFFLINE RL

Learning State Representations from Random Deep Action-conditional Predictions

9 Feb 2021

In this work, we study auxiliary prediction tasks defined by temporal-difference networks (TD networks); these networks are a language for expressing a rich space of general value function (GVF) prediction targets that may be learned efficiently with TD.

ATARI GAMES VALUE PREDICTION

Measuring Progress in Deep Reinforcement Learning Sample Efficiency

9 Feb 2021

Sampled environment transitions are a critical input to deep reinforcement learning (DRL) algorithms.

ATARI GAMES CONTINUOUS CONTROL

An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios

5 Feb 2021

Intelligent robots provide a new insight into efficiency improvement in industrial and service scenarios to replace human labor.

ATARI GAMES MOTION PLANNING

Hierarchical Width-Based Planning and Learning

15 Jan 2021

In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2.

ATARI GAMES

Deep Reinforcement Learning with Quantum-inspired Experience Replay

6 Jan 2021

In this paper, a novel training paradigm inspired by quantum computation is proposed for deep reinforcement learning (DRL) with experience replay.

ATARI GAMES

Unsupervised Active Pre-Training for Reinforcement Learning

1 Jan 2021

On DMControl suite, APT beats all baselines in terms of asymptotic performance and data efficiency and dramatically improves performance on tasks that are extremely difficult for training from scratch.

ATARI GAMES UNSUPERVISED PRE-TRAINING

Deep Q-Learning with Low Switching Cost

1 Jan 2021

We initiate the study on deep reinforcement learning problems that require low switching cost, i. e., small number of policy switches during training.

ATARI GAMES Q-LEARNING RECOMMENDATION SYSTEMS REPRESENTATION LEARNING