Atari 2600

The 'Atari 2600' is a benchmark that contains a collection of ten video games used to evaluate the performance and energy efficiency of various deep reinforcement learning algorithms.

Papers using Atari 2600 (9)

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks2025Deep Double Q-learning2025Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains2025Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound2025Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning2025Group-Agent Reinforcement Learning with Heterogeneous Agents2025Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RL2024 · 3 citesPG-Rainbow: Using Distributional Reinforcement Learning in Policy Gradient Methods2024