Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
T
TutorGym
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
Container 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
GitLab community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Teachable AI Lab
TutorGym
Repository graph
Repository graph
You can move around the graph by using the arrow keys.
c8a36fb1854be984ad958e8bc827633a0be37e55
Select Git revision
Selected
c8a36fb1854be984ad958e8bc827633a0be37e55
Branches
3
master
default
betterInstructions
tact_agent
4 results
Begin with the selected commit
Created with Raphaël 2.2.0
6
Oct
6
May
4
Aug
2
25
Jan
22
21
19
15
5
23
Dec
22
21
14
10
22
Oct
16
13
9
1
30
Sep
28
Updated format string in DataShopLogger to use uppercase %S
master
master
updated run script to restrict range of inputs, updated knowledge to just have conceptual knowledge, working out pseudo code for rule updating.
tact_agent
tact_agent
added code to run tact agent on fractions, simplified fractions output representation to remove the above, left, etc.
changing version for error
betterInstructi…
betterInstructions
making pbr false
v0.1
fixing name
changing name to tutorenvs
setup file
adding instructions
comment and instruction changes
added multi ppo-operator tuned hyperparams
fixed multicolumn bug where agent can receive reward for submitting empty string to a field that should be empty
removed py_rete dependency
added multicolumn run_al
set fractions back to normal difficulty
added operator multicolumn model
mostly working version of ppo tuning/training for fraction operator model
set lower min eval for fraction ppo tuning, disabled logging for multicolumn, added dual decision tree model for fractions
trying to get ppo model working with fractions, had to reduce problem difficulty
updated multicolumn to rename carrys to the column they align with.
latest updates
changed sampling space to be dynamic to match up batches and steps better
added ability to do multiple processes for study in parallel
adjustment to tune ppo
code for tuning ppo
got the dual ppo working, with some of the classes for optuna tuning"
working version of fractions PPO model and decision tree model
working with decision tree and cobweb for tutor env
working version of request_demo for multicolumn addition; datashop logging
working env with eye / perception
working pixel representation for multicolumn
working version of multicolumn
added in soem rendering
working v1 for fractions that abstracts away specific numbers in fields
forgot to include ppo example
working RL model
renamed to lower case
working example with AL
working version of fractions environment
Loading