Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
C
COSC350_550_workshops
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Jonathan Vitale
COSC350_550_workshops
Commits
9767d094
Commit
9767d094
authored
1 year ago
by
Jon
Browse files
Options
Downloads
Patches
Plain Diff
Remove agent program description
parent
fe64daba
No related branches found
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
week3/material/agent_programs.py
+0
-20
0 additions, 20 deletions
week3/material/agent_programs.py
week3/solution/agent_programs.py
+0
-20
0 additions, 20 deletions
week3/solution/agent_programs.py
with
0 additions
and
40 deletions
week3/material/agent_programs.py
+
0
−
20
View file @
9767d094
...
...
@@ -10,26 +10,6 @@ from vacuum_agent import VacuumAgent
DIRECTIONS
=
VacuumAgent
.
WHEELS_DIRECTIONS
"""
Agent implementing a search algorithm:
- The agent must first update the model of the world (a GridMap) with the following information:
1. The current tile set as visited (
'
X
'
)
2. The location of the charging dock (
'
C
'
) given by the sensor
'
charging-dock-location-sensor
'
3. Any wall the agent crashed against (
'
W
'
)
4. The dirt in the adjacent cells (
'
D
'
)
- The agent must start cleaning if it is not currently doing so and stop cleaning if
the whole environment has been cleaned
- The agent must activate the suction mechanism if there is dirt on the current tile
or deactivate it if there is not (to preserve the battery)
- Then, the agent must check the current battery level:
1. If the battery level is below 50%, the agent must use a search algorithm to
head back to the charging dock before getting out of battery
2. Otherwise, the agent must use a search algorithm to head to an unvisited
tile
In both cases, the agent will return an action to change the direction of the
wheels towards the goal state, based on the path found by the search algorithm
"""
# 1. We create a model of the environment using a GridMap
# this step is similar to Week 2 workshop when implementing
# the model based agents
...
...
This diff is collapsed.
Click to expand it.
week3/solution/agent_programs.py
+
0
−
20
View file @
9767d094
...
...
@@ -10,26 +10,6 @@ from vacuum_agent import VacuumAgent
DIRECTIONS
=
VacuumAgent
.
WHEELS_DIRECTIONS
"""
Agent implementing a search algorithm:
- The agent must first update the model of the world (a GridMap) with the following information:
1. The current tile set as visited (
'
X
'
)
2. The location of the charging dock (
'
C
'
) given by the sensor
'
charging-dock-location-sensor
'
3. Any wall the agent crashed against (
'
W
'
)
4. The dirt in the adjacent cells (
'
D
'
)
- The agent must start cleaning if it is not currently doing so and stop cleaning if
the whole environment has been cleaned
- The agent must activate the suction mechanism if there is dirt on the current tile
or deactivate it if there is not (to preserve the battery)
- Then, the agent must check the current battery level:
1. If the battery level is below 50%, the agent must use a search algorithm to
head back to the charging dock before getting out of battery
2. Otherwise, the agent must use a search algorithm to head to an unvisited
tile
In both cases, the agent will return an action to change the direction of the
wheels towards the goal state, based on the path found by the search algorithm
"""
# 1. We create a model of the environment using a GridMap
# this step is similar to Week 2 workshop when implementing
# the model based agents
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment