Atari Chopper Command Environment
Overview
In Chopper Command the player controls a military helicopter in a desert scenario protecting a convoy of trucks. The goal is to destroy all enemy fighter jets and helicopters that attack the player’s helicopter and the friendly trucks traveling below, ending the current wave. The game ends when the player loses all of his or her lives or reaches 999,999 points. A radar, called a Long Range Scanner in the instruction manual, shows all enemies, including those not visible on the main screen.
Description from Wikipedia
Performances of RL Agents
We list various reinforcement learning algorithms that were tested in this environment. These results are from RL Database. If this page was helpful, please consider giving a star!
Human Starts
No-op Starts
Normal Starts
Result | Algorithm | Source |
---|---|---|
5287.7 | ACER | Proximal Policy Optimization Algorithm |
3516.3 | PPO | Proximal Policy Optimization Algorithm |
2070 | DRQN | Deep Recurrent Q-Learning for Partially Observable MDPs |
1460 | DQN Ours | Deep Recurrent Q-Learning for Partially Observable MDPs |
1450 | DQN Ours | Deep Recurrent Q-Learning for Partially Observable MDPs |
1330 | DRQN | Deep Recurrent Q-Learning for Partially Observable MDPs |
1171.7 | A2C | Proximal Policy Optimization Algorithm |