Overview
The gameplay of Ms. Pac-Man is very similar to that of the original Pac-Man. The player earns points by eating pellets and avoiding ghosts (contact with one causes Ms. Pac-Man to lose a life). Eating an energizer (or “power pellet”) causes the ghosts to turn blue, allowing them to be eaten for extra points. Bonus fruits can be eaten for increasing point values, twice per round. As the rounds increase, the speed increases, and energizers generally lessen the duration of the ghosts’ vulnerability, eventually stopping altogether.
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 |
---|---|---|
3908.105 | ACER | RL Baselines Zoo b76641e |
2718.5 | ACER | Proximal Policy Optimization Algorithm |
2363 | DQN Ours | Deep Recurrent Q-Learning for Partially Observable MDPs |
2255.09 | PPO | RL Baselines Zoo b76641e |
2096.5 | PPO | Proximal Policy Optimization Algorithm |
2048 | DRQN | Deep Recurrent Q-Learning for Partially Observable MDPs |
1824 | DQN Ours | Deep Recurrent Q-Learning for Partially Observable MDPs |
1781.818 | DQN | RL Baselines Zoo b76641e |
1739 | DRQN | Deep Recurrent Q-Learning for Partially Observable MDPs |
1626.9 | A2C | Proximal Policy Optimization Algorithm |
1598.776 | ACKTR | RL Baselines Zoo b76641e |
1581.111 | A2C | RL Baselines Zoo b76641e |