Dqn BreakoutNoFrameskip V4
This is a deep reinforcement learning model based on the DQN algorithm, specifically designed for the Atari game environment BreakoutNoFrameskip-v4.
Downloads 20
Release Time : 6/2/2022
Model Overview
The model is trained using the DQN algorithm from the stable-baselines3 library and can achieve high average scores in the Breakout game.
Model Features
Frame stacking processing
Uses 4-frame stacking technique to capture game dynamics information
Efficient exploration strategy
Employs epsilon-greedy exploration strategy with exploration rate decaying from initial value to 0.01
Optimized memory usage
Enabled memory optimization options to improve training efficiency
Model Capabilities
Atari game control
Reinforcement learning decision-making
Pixel-level input processing
Use Cases
Game AI
Breakout game AI
Automatically plays Atari Breakout game
Average score 359±44.32
Reinforcement learning research
DQN algorithm benchmark
Serves as a benchmark model for deep Q-learning algorithms
Featured Recommended AI Models