Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
A
advice
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
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
Philipp Sauer
advice
Repository graph
Repository graph
You can move around the graph by using the arrow keys.
6f419c6398dba268c1de530a2169ab6278f50aad
Select Git revision
Branches
2
master
default
protected
pytorch
2 results
Begin with the selected commit
Created with Raphaël 2.2.0
17
Apr
16
15
14
13
12
11
10
31
Mar
17
13
9
8
3
27
Feb
26
10
Jul
22
May
21
20
15
14
3
1
29
Apr
26
22
19
Updated requirements
pytorch
pytorch
Vectorized main
Added ADVICE stuff, punish rewards
Some train logging
Added eval
Cosmetic changes
Added neighbours_count adapivity
Added weight_decay to fc1
Added interval advice style sampling
Added debug and visualization
Added shielding
Removed sigmoid activation in decoder
Working version that trains the autoencoder and knn, still some todos
Updated requirements
Removed files
Adjustments
added custom_benchmarks support
Deleted benchmarks directory
Used with context for writer
master
master
Adjusted env creation
Refactoring, small changes
Replaced list with deque for safe obs
Added mid_obstacle env
Removed episode_goal_reaches in training
Reworked cost and goal_met logic
Removed safety_violations logging for each episode
Added pendulum and car_racing
Added kwargs to road_2d
Bugfix state_slice_indices default value
Added road2d env
Added evaluation
Modified tensorboard logging
added hidden_dim arg
Added mask to buffer, minor changes to args
Added total_episodes logging
Added state_slice_indices
Added racetrack, added option to modify safetygym env
Updated args
Updated requirements
Initial rework
Loading