Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
B
baselines
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
Model registry
Operate
Environments
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
Flatland
baselines
Graph
af03b004359892f1df22b2ce30a751cca4e647ee
Select Git revision
Branches
7
2-cleanup-baselines
3-refactor-data-structure-of-treeobsforrailenv
feature/testing_obs
master
default
testing_a3c
update-baselines
wandb
7 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
7
Jul
9
Jun
16
May
8
27
Apr
7
Nov
27
Oct
26
24
9
7
6
5
2
1
30
Sep
27
26
24
12
1
31
Aug
29
28
27
14
12
31
Jul
26
25
23
19
18
17
16
15
11
10
9
8
6
5
3
2
1
29
Jun
28
27
25
24
22
16
15
14
13
12
11
9
7
6
5
29
May
24
23
22
21
20
19
17
15
14
13
Trying to make evaluations deterministic
master
master
Update multi_agent_inference.py
Update multi_agent_training.py
Update render_agent_behavior.py
Update training_navigation.py
Update training_navigation.py
Update render_agent_behavior.py
Update multi_agent_training.py
Update multi_agent_inference.py
Update render_agent_behavior.py
Update multi_agent_training.py
Update training_navigation.py
minor changes
feature/testing…
feature/testing_obs
initial commit
Basic wandb reporting
wandb
wandb
Merge branch 'master' of gitlab.aicrowd.com:flatland/baselines
updated files to new malfunction behavior
updated training file to max time and added multi speed and stochasticity
updated training file to max time and added multi speed and stochasticity
updated multi agent training for testing
catchin error with None observation
updated traiing files
added shortest path predictor to multi agent training and inference
updated multi/agent inference
updated multi-agent training
Changed renderEnv to render_env
removed "bug" with reward. Attention, currently it is cheaper for an agent to wait if we cummulate rewards between the different state!
removed "bug" with reward. Attention, currently it is cheaper for an agent to wait if we cummulate rewards between the different state!
updated training file
updated training for single agent navigation to be compatible with new env
updated training file
minor bugfixes
updated to new reset behavior
penalizing waiting agent in order to get them on the field.
updated single agent navigation to work with new env
minor bugfixes
Merge branch 'patch-1' into 'master'
Merge branch '3-refactor-data-structure-of-treeobsforrailenv' into 'master'
Fix typos
refactor tree data structure and add unit test for the normalization of the features
3-refactor-data…
3-refactor-data-structure-of-treeobsforrailenv
Loading