Atari Games
277 papers with code • 64 benchmarks • 6 datasets
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
These leaderboards are used to track progress in Atari Games
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Atari Games models and implementationsDatasets
Arcade Learning Environment
DQN Replay Dataset
Atari-HEAD
Atari Grand Challenge
AtariARI
RLU
Latest papers
A Robust Quantile Huber Loss With Interpretable Parameter Adjustment In Distributional Reinforcement Learning
pmalekzadeh/A-robust-quantile-huber-loss
•
•
Distributional Reinforcement Learning (RL) estimates return distribution mainly by learning quantile values via minimizing the quantile Huber loss function, entailing a threshold parameter often selected heuristically or via hyperparameter search, which may not generalize well and can be suboptimal.
Active Reinforcement Learning for Robust Building Control
Reinforcement learning (RL) is a powerful tool for optimal control that has found great success in Atari games, the game of Go, robotic control, and building optimization.
Distributional Bellman Operators over Mean Embeddings
google-deepmind/sketch_dqn
•
•
We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions.
Absolute Policy Optimization
intelligent-control-lab/absolute-policy-optimization
•
•
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios.
MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
This paper presents MiniZero, a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero.
PGDQN: Preference-Guided Deep Q-Network
OscarHuangWind/Preference-Guided-DQN-Atari
•
•
IEEE Transactions on Neural Networks and Learning Systems 2023
Stochastic exploration is the key to the success of the Deep Q-network (DQN) algorithm.
Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments
Understanding the interactions of agents trained with deep reinforcement learning is crucial for deploying agents in games or the real world.
Beyond Surprise: Improving Exploration Through Surprise Novelty
thaihungle/sm
•
•
We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations.
Approximate Model-Based Shielding for Safe Reinforcement Learning
sacktock/ambs
•
•
Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains.
OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
In our work, we extend the Atari Learning Environments, the most-used evaluation framework for deep RL approaches, by introducing OCAtari, that performs resource-efficient extractions of the object-centric states for these games.
