Skip to content

Commit 2a9077b

Browse files
pseudo-rnd-thoughtspseudo-rnd-thoughts
authored
Improve atari documentation through using multiple columns for the actions table (#394)
1 parent a6672ba commit 2a9077b

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

107 files changed

+741
-1616
lines changed

Diff for: ‎docs/api/experimental.md

+1
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,7 @@ experimental/functional
1010
experimental/wrappers
1111
experimental/vector
1212
experimental/vector_wrappers
13+
experimental/vector_utils
1314
```
1415

1516
## Functional Environments

Diff for: ‎docs/environments/atari.md

+10-20
Original file line numberDiff line numberDiff line change
@@ -133,26 +133,16 @@ It is possible to install the ROMs in an alternative location, [AutoROM](https:/
133133

134134
Each environment will use a sub-set of the full action space listed below:
135135

136-
| Num | Action |
137-
|-----|---------------|
138-
| 0 | NOOP |
139-
| 1 | FIRE |
140-
| 2 | UP |
141-
| 3 | RIGHT |
142-
| 4 | LEFT |
143-
| 5 | DOWN |
144-
| 6 | UPRIGHT |
145-
| 7 | UPLEFT |
146-
| 8 | DOWNRIGHT |
147-
| 9 | DOWNLEFT |
148-
| 10 | UPFIRE |
149-
| 11 | RIGHTFIRE |
150-
| 12 | LEFTFIRE |
151-
| 13 | DOWNFIRE |
152-
| 14 | UPRIGHTFIRE |
153-
| 15 | UPLEFTFIRE |
154-
| 16 | DOWNRIGHTFIRE |
155-
| 17 | DOWNLEFTFIRE |
136+
| Value | Meaning | Value | Meaning | Value | Meaning |
137+
|---------|--------------|---------|-----------------|---------|----------------|
138+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
139+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `DOWN` |
140+
| `6` | `UPRIGHT` | `7` | `UPLEFT` | `8` | `DOWNRIGHT` |
141+
| `9` | `DOWNLEFT` | `10` | `UPFIRE` | `11` | `RIGHTFIRE` |
142+
| `12` | `LEFTFIRE` | `13` | `DOWNFIRE` | `14` | `UPRIGHTFIRE` |
143+
| `15` | `UPLEFTFIRE` | `16` | `DOWNRIGHTFIRE` | `17` | `DOWNLEFTFIRE` |
144+
145+
156146

157147
By default, most environments use a smaller subset of the legal actions excluding any actions that don't have an effect in the game.
158148
If users are interested in using all possible actions, pass the keyword argument `full_action_space=True` to `gymnasium.make`.

Diff for: ‎docs/environments/atari/adventure.md

+9-21
Original file line numberDiff line numberDiff line change
@@ -25,33 +25,21 @@ For more Adventure variants with different observation and action spaces, see th
2525

2626
You must find the enchanted chalice and return it to the golden castle. You can pick up various objects (keys, a sword,a bridge, or a magnet) and have to fight or outmanoeuvre dragons.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1)
2929

3030
## Actions
3131

3232
Adventure has the action space `Discrete(18)` with the table below lists the meaning of each action's meanings.
3333
As Adventure uses the full set of actions then specifying `full_action_space=True` will not modify the action space of the environment if passed to `gymnasium.make`.
3434

35-
| Value | Meaning |
36-
|---------|-----------------|
37-
| `0` | `NOOP` |
38-
| `1` | `FIRE` |
39-
| `2` | `UP` |
40-
| `3` | `RIGHT` |
41-
| `4` | `LEFT` |
42-
| `5` | `DOWN` |
43-
| `6` | `UPRIGHT` |
44-
| `7` | `UPLEFT` |
45-
| `8` | `DOWNRIGHT` |
46-
| `9` | `DOWNLEFT` |
47-
| `10` | `UPFIRE` |
48-
| `11` | `RIGHTFIRE` |
49-
| `12` | `LEFTFIRE` |
50-
| `13` | `DOWNFIRE` |
51-
| `14` | `UPRIGHTFIRE` |
52-
| `15` | `UPLEFTFIRE` |
53-
| `16` | `DOWNRIGHTFIRE` |
54-
| `17` | `DOWNLEFTFIRE` |
35+
| Value | Meaning | Value | Meaning | Value | Meaning |
36+
|---------|--------------|---------|-----------------|---------|----------------|
37+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
38+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `DOWN` |
39+
| `6` | `UPRIGHT` | `7` | `UPLEFT` | `8` | `DOWNRIGHT` |
40+
| `9` | `DOWNLEFT` | `10` | `UPFIRE` | `11` | `RIGHTFIRE` |
41+
| `12` | `LEFTFIRE` | `13` | `DOWNFIRE` | `14` | `UPRIGHTFIRE` |
42+
| `15` | `UPLEFTFIRE` | `16` | `DOWNRIGHTFIRE` | `17` | `DOWNLEFTFIRE` |
5543

5644
## Observations
5745

Diff for: ‎docs/environments/atari/air_raid.md

+4-8
Original file line numberDiff line numberDiff line change
@@ -32,14 +32,10 @@ As AirRaid uses a reduced set of actions for `v0`, `v4` and `v5` versions of the
3232
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3333
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3434

35-
| Value | Meaning |
36-
|---------|-------------|
37-
| `0` | `NOOP` |
38-
| `1` | `FIRE` |
39-
| `2` | `RIGHT` |
40-
| `3` | `LEFT` |
41-
| `4` | `RIGHTFIRE` |
42-
| `5` | `LEFTFIRE` |
35+
| Value | Meaning | Value | Meaning | Value | Meaning |
36+
|---------|-----------|---------|-------------|---------|------------|
37+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `RIGHT` |
38+
| `3` | `LEFT` | `4` | `RIGHTFIRE` | `5` | `LEFTFIRE` |
4339

4440
## Observations
4541

Diff for: ‎docs/environments/atari/alien.md

+9-21
Original file line numberDiff line numberDiff line change
@@ -25,33 +25,21 @@ For more Alien variants with different observation and action spaces, see the va
2525

2626
You are stuck in a maze-like space ship with three aliens. You goal is to destroy their eggs that are scattered all over the ship while simultaneously avoiding the aliens (they are trying to kill you). You have a flamethrower that can help you turn them away in tricky situations. Moreover, you can occasionally collect a power-up (pulsar) that gives you the temporary ability to kill aliens.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=815)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=815)
2929

3030
## Actions
3131

3232
Alien has the action space `Discrete(18)` with the table below lists the meaning of each action's meanings.
3333
As Alien uses the full set of actions then specifying `full_action_space=True` will not modify the action space of the environment if passed to `gymnasium.make`.
3434

35-
| Value | Meaning |
36-
|---------|-----------------|
37-
| `0` | `NOOP` |
38-
| `1` | `FIRE` |
39-
| `2` | `UP` |
40-
| `3` | `RIGHT` |
41-
| `4` | `LEFT` |
42-
| `5` | `DOWN` |
43-
| `6` | `UPRIGHT` |
44-
| `7` | `UPLEFT` |
45-
| `8` | `DOWNRIGHT` |
46-
| `9` | `DOWNLEFT` |
47-
| `10` | `UPFIRE` |
48-
| `11` | `RIGHTFIRE` |
49-
| `12` | `LEFTFIRE` |
50-
| `13` | `DOWNFIRE` |
51-
| `14` | `UPRIGHTFIRE` |
52-
| `15` | `UPLEFTFIRE` |
53-
| `16` | `DOWNRIGHTFIRE` |
54-
| `17` | `DOWNLEFTFIRE` |
35+
| Value | Meaning | Value | Meaning | Value | Meaning |
36+
|---------|--------------|---------|-----------------|---------|----------------|
37+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
38+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `DOWN` |
39+
| `6` | `UPRIGHT` | `7` | `UPLEFT` | `8` | `DOWNRIGHT` |
40+
| `9` | `DOWNLEFT` | `10` | `UPFIRE` | `11` | `RIGHTFIRE` |
41+
| `12` | `LEFTFIRE` | `13` | `DOWNFIRE` | `14` | `UPRIGHTFIRE` |
42+
| `15` | `UPLEFTFIRE` | `16` | `DOWNRIGHTFIRE` | `17` | `DOWNLEFTFIRE` |
5543

5644
## Observations
5745

Diff for: ‎docs/environments/atari/amidar.md

+7-13
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ For more Amidar variants with different observation and action spaces, see the v
2525

2626
This game is similar to Pac-Man: You are trying to visit all places on a 2-dimensional grid while simultaneously avoiding your enemies. You can turn the tables at one point in the game: Your enemies turn into chickens and you can catch them.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=817)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=817)
2929

3030
## Actions
3131

@@ -34,18 +34,12 @@ As Amidar uses a reduced set of actions for `v0`, `v4` and `v5` versions of the
3434
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3535
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3636

37-
| Value | Meaning |
38-
|---------|-------------|
39-
| `0` | `NOOP` |
40-
| `1` | `FIRE` |
41-
| `2` | `UP` |
42-
| `3` | `RIGHT` |
43-
| `4` | `LEFT` |
44-
| `5` | `DOWN` |
45-
| `6` | `UPFIRE` |
46-
| `7` | `RIGHTFIRE` |
47-
| `8` | `LEFTFIRE` |
48-
| `9` | `DOWNFIRE` |
37+
| Value | Meaning | Value | Meaning | Value | Meaning |
38+
|---------|------------|---------|-------------|---------|------------|
39+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
40+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `DOWN` |
41+
| `6` | `UPFIRE` | `7` | `RIGHTFIRE` | `8` | `LEFTFIRE` |
42+
| `9` | `DOWNFIRE` | | | | |
4943

5044
## Observations
5145

Diff for: ‎docs/environments/atari/assault.md

+6-10
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ For more Assault variants with different observation and action spaces, see the
2525

2626
You control a vehicle that can move sideways. A big mother ship circles overhead and continually deploys smaller drones.You must destroy these enemies and dodge their attacks.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=827)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=827)
2929

3030
## Actions
3131

@@ -34,15 +34,11 @@ As Assault uses a reduced set of actions for `v0`, `v4` and `v5` versions of the
3434
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3535
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3636

37-
| Value | Meaning |
38-
|---------|-------------|
39-
| `0` | `NOOP` |
40-
| `1` | `FIRE` |
41-
| `2` | `UP` |
42-
| `3` | `RIGHT` |
43-
| `4` | `LEFT` |
44-
| `5` | `RIGHTFIRE` |
45-
| `6` | `LEFTFIRE` |
37+
| Value | Meaning | Value | Meaning | Value | Meaning |
38+
|---------|------------|---------|-----------|---------|-------------|
39+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
40+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `RIGHTFIRE` |
41+
| `6` | `LEFTFIRE` | | | | |
4642

4743
## Observations
4844

Diff for: ‎docs/environments/atari/asterix.md

+6-12
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ For more Asterix variants with different observation and action spaces, see the
2525

2626
You are Asterix and can move horizontally (continuously) and vertically (discretely). Objects move horizontally across the screen: lyres and other (more useful) objects. Your goal is to guideAsterix in such a way as to avoid lyres and collect as many other objects as possible. You score points by collecting objects and lose a life whenever you collect a lyre. You have three lives available at the beginning. If you score sufficiently many points, you will be awarded additional points.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=3325)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=3325)
2929

3030
## Actions
3131

@@ -34,17 +34,11 @@ As Asterix uses a reduced set of actions for `v0`, `v4` and `v5` versions of the
3434
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3535
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3636

37-
| Value | Meaning |
38-
|---------|-------------|
39-
| `0` | `NOOP` |
40-
| `1` | `UP` |
41-
| `2` | `RIGHT` |
42-
| `3` | `LEFT` |
43-
| `4` | `DOWN` |
44-
| `5` | `UPRIGHT` |
45-
| `6` | `UPLEFT` |
46-
| `7` | `DOWNRIGHT` |
47-
| `8` | `DOWNLEFT` |
37+
| Value | Meaning | Value | Meaning | Value | Meaning |
38+
|---------|-----------|---------|-------------|---------|------------|
39+
| `0` | `NOOP` | `1` | `UP` | `2` | `RIGHT` |
40+
| `3` | `LEFT` | `4` | `DOWN` | `5` | `UPRIGHT` |
41+
| `6` | `UPLEFT` | `7` | `DOWNRIGHT` | `8` | `DOWNLEFT` |
4842

4943
## Observations
5044

Diff for: ‎docs/environments/atari/asteroids.md

+8-17
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ For more Asteroids variants with different observation and action spaces, see th
2525

2626
This is a well-known arcade game: You control a spaceship in an asteroid field and must break up asteroids by shooting them. Once all asteroids are destroyed, you enter a new level and new asteroids will appear. You will occasionally be attacked by a flying saucer.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=828)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=828)
2929

3030
## Actions
3131

@@ -34,22 +34,13 @@ As Asteroids uses a reduced set of actions for `v0`, `v4` and `v5` versions of t
3434
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3535
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3636

37-
| Value | Meaning |
38-
|---------|---------------|
39-
| `0` | `NOOP` |
40-
| `1` | `FIRE` |
41-
| `2` | `UP` |
42-
| `3` | `RIGHT` |
43-
| `4` | `LEFT` |
44-
| `5` | `DOWN` |
45-
| `6` | `UPRIGHT` |
46-
| `7` | `UPLEFT` |
47-
| `8` | `UPFIRE` |
48-
| `9` | `RIGHTFIRE` |
49-
| `10` | `LEFTFIRE` |
50-
| `11` | `DOWNFIRE` |
51-
| `12` | `UPRIGHTFIRE` |
52-
| `13` | `UPLEFTFIRE` |
37+
| Value | Meaning | Value | Meaning | Value | Meaning |
38+
|---------|---------------|---------|--------------|---------|------------|
39+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
40+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `DOWN` |
41+
| `6` | `UPRIGHT` | `7` | `UPLEFT` | `8` | `UPFIRE` |
42+
| `9` | `RIGHTFIRE` | `10` | `LEFTFIRE` | `11` | `DOWNFIRE` |
43+
| `12` | `UPRIGHTFIRE` | `13` | `UPLEFTFIRE` | | |
5344

5445
## Observations
5546

Diff for: ‎docs/environments/atari/atlantis.md

+5-7
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@ For more Atlantis variants with different observation and action spaces, see the
2525

2626
Your job is to defend the submerged city of Atlantis. Your enemies slowly descend towards the city and you must destroy them before they reach striking distance. To this end, you control three defense posts.You lose if your enemies manage to destroy all seven of Atlantis' installations. You may rebuild installations after you have fought of a wave of enemies and scored a sufficient number of points.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=835)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareID=835)
2929

3030
## Actions
3131

@@ -34,12 +34,10 @@ As Atlantis uses a reduced set of actions for `v0`, `v4` and `v5` versions of th
3434
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3535
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3636

37-
| Value | Meaning |
38-
|---------|-------------|
39-
| `0` | `NOOP` |
40-
| `1` | `FIRE` |
41-
| `2` | `RIGHTFIRE` |
42-
| `3` | `LEFTFIRE` |
37+
| Value | Meaning | Value | Meaning | Value | Meaning |
38+
|---------|------------|---------|-----------|---------|-------------|
39+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `RIGHTFIRE` |
40+
| `3` | `LEFTFIRE` | | | | |
4341

4442
## Observations
4543

Diff for: ‎docs/environments/atari/atlantis2.md

+4-6
Original file line numberDiff line numberDiff line change
@@ -32,12 +32,10 @@ As Atlantis2 uses a reduced set of actions for `v0`, `v4` and `v5` versions of t
3232
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3333
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3434

35-
| Value | Meaning |
36-
|---------|-------------|
37-
| `0` | `NOOP` |
38-
| `1` | `FIRE` |
39-
| `2` | `RIGHTFIRE` |
40-
| `3` | `LEFTFIRE` |
35+
| Value | Meaning | Value | Meaning | Value | Meaning |
36+
|---------|------------|---------|-----------|---------|-------------|
37+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `RIGHTFIRE` |
38+
| `3` | `LEFTFIRE` | | | | |
4139

4240
## Observations
4341

Diff for: ‎docs/environments/atari/backgammon.md

+3-5
Original file line numberDiff line numberDiff line change
@@ -32,11 +32,9 @@ As Backgammon uses a reduced set of actions for `v0`, `v4` and `v5` versions of
3232
To enable all 18 possible actions that can be performed on an Atari 2600, specify `full_action_space=True` during
3333
initialization or by passing `full_action_space=True` to `gymnasium.make`.
3434

35-
| Value | Meaning |
36-
|---------|-----------|
37-
| `0` | `FIRE` |
38-
| `1` | `RIGHT` |
39-
| `2` | `LEFT` |
35+
| Value | Meaning | Value | Meaning | Value | Meaning |
36+
|---------|-----------|---------|-----------|---------|-----------|
37+
| `0` | `FIRE` | `1` | `RIGHT` | `2` | `LEFT` |
4038

4139
## Observations
4240

Diff for: ‎docs/environments/atari/bank_heist.md

+9-21
Original file line numberDiff line numberDiff line change
@@ -25,33 +25,21 @@ For more BankHeist variants with different observation and action spaces, see th
2525

2626
You are a bank robber and (naturally) want to rob as many banks as possible. You control your getaway car and must navigate maze-like cities. The police chases you and will appear whenever you rob a bank. You may destroy police cars by dropping sticks of dynamite. You can fill up your gas tank by entering a new city.At the beginning of the game you have four lives. Lives are lost if you run out of gas, are caught by the police,or run over the dynamite you have previously dropped.
2727

28-
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1008)
28+
For a more detailed documentation, see [the AtariAge page](https://atariage.com/manual_html_page.php?SoftwareLabelID=1008)
2929

3030
## Actions
3131

3232
BankHeist has the action space `Discrete(18)` with the table below lists the meaning of each action's meanings.
3333
As BankHeist uses the full set of actions then specifying `full_action_space=True` will not modify the action space of the environment if passed to `gymnasium.make`.
3434

35-
| Value | Meaning |
36-
|---------|-----------------|
37-
| `0` | `NOOP` |
38-
| `1` | `FIRE` |
39-
| `2` | `UP` |
40-
| `3` | `RIGHT` |
41-
| `4` | `LEFT` |
42-
| `5` | `DOWN` |
43-
| `6` | `UPRIGHT` |
44-
| `7` | `UPLEFT` |
45-
| `8` | `DOWNRIGHT` |
46-
| `9` | `DOWNLEFT` |
47-
| `10` | `UPFIRE` |
48-
| `11` | `RIGHTFIRE` |
49-
| `12` | `LEFTFIRE` |
50-
| `13` | `DOWNFIRE` |
51-
| `14` | `UPRIGHTFIRE` |
52-
| `15` | `UPLEFTFIRE` |
53-
| `16` | `DOWNRIGHTFIRE` |
54-
| `17` | `DOWNLEFTFIRE` |
35+
| Value | Meaning | Value | Meaning | Value | Meaning |
36+
|---------|--------------|---------|-----------------|---------|----------------|
37+
| `0` | `NOOP` | `1` | `FIRE` | `2` | `UP` |
38+
| `3` | `RIGHT` | `4` | `LEFT` | `5` | `DOWN` |
39+
| `6` | `UPRIGHT` | `7` | `UPLEFT` | `8` | `DOWNRIGHT` |
40+
| `9` | `DOWNLEFT` | `10` | `UPFIRE` | `11` | `RIGHTFIRE` |
41+
| `12` | `LEFTFIRE` | `13` | `DOWNFIRE` | `14` | `UPRIGHTFIRE` |
42+
| `15` | `UPLEFTFIRE` | `16` | `DOWNRIGHTFIRE` | `17` | `DOWNLEFTFIRE` |
5543

5644
## Observations
5745

0 commit comments

Comments
 (0)