Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
Update game list
  • Loading branch information
BluemlJ authored Feb 2, 2024
1 parent ce2bb7c commit a67369a
Showing 1 changed file with 21 additions and 7 deletions.
28 changes: 21 additions & 7 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -58,45 +58,58 @@ year={2023}
```

### List of covered games
- [ ] Alien (only vision)
- [X] Alien
- [X] Amidar
- [X] Assault
- [X] Asterix
- [ ] Asteroids (only vision)
- [X] Asteroids (only vision)
- [X] Atlantis
- [ ] BattleZone (in progress)
- [ ] Bankheist (in progress)
- [ ] BeamRider (only vision)
- [X] Berzerk
- [X] Bowling
- [X] Boxing
- [X] Breakout
- [X] Carnival
- [X] Centipede
- [X] Chopper Command
- [X] Chopper Command
- [X] Crazy Climbers
- [X] DemonAttack
- [X] Fishing Derby
- [X] Freeway
- [X] Frostbite
- [X] Frostbite
- [X] Gopher
- [X] Hero
- [X] IceHockey
- [X] Kangaroo
- [X] Krull
- [X] MontezumaRevenge
- [X] MsPacman
- [X] Pitfall
- [X] Pong
- [X] PrivateEye
- [X] Q\*Bert
- [X] RiverRaid
- [X] RoadRunner
- [X] Seaquest
- [X] Skiing
- [X] Space Invaders
- [X] Tennis
- [X] Time Pilot
- [ ] Up n Down (in progress)
- [X] Venture
- [X] VideoPinball
- [ ] YarsRevenge
- [ ] YarsRevenge (in progress)

A list of all gymnasium games can be found in the [Gymnasium Documentation](https://gymnasium.farama.org/environments/atari/)

### The two modes of OCAtari
OCAtari supports two different modes to extract objects from the current state:

**Vision Extraction Mode:** Return a list of objects currently on the screen with their X, Y, Width, Height, R, G, B Values, based on handwritten rules used on the visual representation.
**Vision Extraction Mode (VEM):** Return a list of objects currently on the screen with their X, Y, Width, Height, R, G, B Values, based on handwritten rules used on the visual representation.

**Ram Extraction Mode:** Uses the object values stored in the RAM to detect the objects currently on the screen.
**Ram Extraction Mode (REM):** Uses the object values stored in the RAM to detect the objects currently on the screen.

### Use these trained agents and the demo script:

Expand All @@ -109,6 +122,7 @@ Here is an example:
`python demo_pong.py -p models/Pong/model_50000000.gz`

More information can be found in this [ReadMe](scripts/demo/README%20Demos.md)

### Extract the objects from a state

With `env.objects` one can access the list of objects found in the current state. Note that these lists can differ depending on the mode you used initiating the environment
Expand Down

0 comments on commit a67369a

Please sign in to comment.