Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
D
DQN-NMT
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
Container Registry
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
rios
DQN-NMT
Graph
2d7af05dd8a10b64b358a79f83a9c739c001d111
Select Git revision
Branches
4
carlosV0
final
final_batch-version
master
default
protected
4 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
4
May
3
2
1
28
Apr
27
24
13
12
10
6
5
4
3
2
1
31
Mar
30
29
26
25
24
23
22
21
17
16
Update README.md file.
master
master
Update README.md file.
README file updated.
final_batch-ver…
final_batch-version
Merge branch 'final_batch-version' of https://gitlab.cl.uni-heidelberg.de/rios/DQN-NMT into final_batch-version
small config file added.
Update README.md
Update README.md
Commented and clean code.
Cleaning of the config files.
final
final
Documented version of the code.
nada
carlosV0
carlosV0
sligth change
sligth change
Adding the last dataset, 100 samples.
Update mini_reverse_1_1_1_5_5.yaml
showing the right values on tensorboard
Deletd the line model dir for colab.
script to modify hyperparamters.
Changed on rigth values on configs files..
Fixing the right model dir to work on Colab
Fixing the error on size states
Fixing the error on size states
Cahnge name of dataset, to fit sintaxis
Adding scripts and configs files nedded
Solving conflicts with mergin
Adding the needed datasets. one_reverse and mini_reverse_2000_200_200_5_5
tests with one sequence.
Added the entropy and stop criteria
Setting to reproduce results.
Trying a under-trained Actor, on the current version of DQN. On mini reverse task
Testing several handcrafted rewards.
Dev from Antonios branch, currently havin on mini_reverse_task an stable bleu score of 50.92, using the bleu_seq score
simplfied version bleu_diff
New feature to see different tests in tesorboard added, based on the date and some relevan hyperparameters.
true action used
Merge branch 'master' into antonio_v1.1
add true action in Bellman equation
true action done
Use the true action
Conflicts resolved
Loading