Atari Games

276 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 )

Libraries

Use these libraries to find Atari Games models and implementations
12 papers
2,399
11 papers
1,150
7 papers
2,302
See all 23 libraries.

Latest papers with no code

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

no code yet • 6 Mar 2024

Observing this discrepancy, in this paper, we investigate whether the scalability of deep RL can also be improved simply by using classification in place of regression for training value functions.

Iterated $Q$-Network: Beyond the One-Step Bellman Operator

no code yet • 4 Mar 2024

Value-based Reinforcement Learning (RL) methods rely on the application of the Bellman operator, which needs to be approximated from samples.

Disentangling the Causes of Plasticity Loss in Neural Networks

no code yet • 29 Feb 2024

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution.

Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning

no code yet • 11 Feb 2024

We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks.

Solving Deep Reinforcement Learning Benchmarks with Linear Policy Networks

no code yet • 10 Feb 2024

Although Deep Reinforcement Learning (DRL) methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex and training times are often long.

Neural Policy Style Transfer

no code yet • 1 Feb 2024

The implementation of three different Q-Network architectures (Shallow, Deep and Deep Recurrent Q-Network) to encode the policies within the NPST framework is proposed and the results obtained in the experiments with each of these architectures compared.

Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approach

no code yet • 1 Feb 2024

In this paper we are introducing a new reinforcement learning method for control problems in environments with delayed feedback.

Look Around! Unexpected gains from training on environments in the vicinity of the target

no code yet • 29 Jan 2024

Here we present a new methodology to evaluate such generalization of RL agents under small shifts in the transition probabilities.

Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games

no code yet • 4 Dec 2023

Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community.

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

no code yet • 28 Nov 2023

Instead, we employ a proxy model to extract state features that are both discriminative (adaptive to the agent) and generally applicable (robust to agent noise).