Atari Double Dunk Environment
Overview
Double Dunk is a simulation of two-on-two, half-court basketball. Teams have two on-screen characters, a shorter “outside” man and a taller “inside” man. In a single-player game, the player controls the on-screen character closest to the ball, either the one holding the ball (on offense) or the one guarding the opponent with the ball (on defense). In two-player games, each player may control one of the two teams as in a one-player game, or both players may play on the same team against a computer-controlled opponent. At the start of each possession, both offense and defense select from a number of plays (such as the “pick and roll” on offense), then attempt to score or regain possession of the ball by intercepting or stealing it from the offense.
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 |
---|---|---|
-2 | DRQN | Deep Recurrent Q-Learning for Partially Observable MDPs |
-10 | DQN Ours | Deep Recurrent Q-Learning for Partially Observable MDPs |
-13.2 | ACER | Proximal Policy Optimization Algorithm |
-14 | DRQN | Deep Recurrent Q-Learning for Partially Observable MDPs |
-14.9 | PPO | Proximal Policy Optimization Algorithm |
-16.2 | DQN Ours | Deep Recurrent Q-Learning for Partially Observable MDPs |
-16.2 | A2C | Proximal Policy Optimization Algorithm |