nilscrm stackelberg-ml issues

nilscrm / stackelberg-ml

0 stars 0 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Sample efficiency

#42 Angramme opened 4 months ago
0
More Sample Efficient MAL

#41 YanickZengaffinen opened 4 months ago
3
MBRL Inner Loop To Convergence

#40 YanickZengaffinen opened 4 months ago
0
Write Report

#39 YanickZengaffinen opened 5 months ago
1
More MDPs + evaluations

#38 nilscrm closed 5 months ago
0
MAL + Agent Reward Optimality

#37 YanickZengaffinen closed 4 months ago
3
Context helpful for POMDP?

#36 YanickZengaffinen opened 5 months ago
0
PAL reduces to standard MBRL?

#35 YanickZengaffinen opened 5 months ago
0
Example: Ergodicity + Deterministic

#34 YanickZengaffinen opened 5 months ago
4
Reset tensorboard steps count correctly

#33 nilscrm closed 5 months ago
0
Implement PAL

#32 nilscrm closed 5 months ago
0
Theoretic Analysis

#31 nilscrm closed 4 months ago
3
Investigate sample efficiency.

#30 Angramme opened 5 months ago
6
Leader Training With Actual Reward Of Policy

#29 YanickZengaffinen closed 5 months ago
0
KLDiv for Model

#28 YanickZengaffinen opened 5 months ago
0
KLDiv instead of MSE

#27 YanickZengaffinen opened 5 months ago
1
Refactoring Codebase

#26 nilscrm closed 5 months ago
0
Try out PAL?

#25 nilscrm closed 5 months ago
4
Clean up experiment config

#24 nilscrm opened 5 months ago
0
Train the model on an RL environment that first queries the leader

#23 nilscrm closed 5 months ago
0
Minimal Guarantees For SE

#22 YanickZengaffinen opened 5 months ago
2
Impact of Flawed Objective

#21 YanickZengaffinen opened 5 months ago
3
MBRL Inner Loop To Convergence

#20 YanickZengaffinen closed 4 months ago
2
Inject Random Samples

#19 YanickZengaffinen closed 5 months ago
2
Experiment to evaluate pretrained policy

#18 nilscrm closed 6 months ago
1
Create package for our code

#17 nilscrm closed 6 months ago
0
Evaluate pretrained policy model

#16 nilscrm closed 5 months ago
2
Make Poster

#15 YanickZengaffinen closed 5 months ago
0
Env-Sample Counting

#14 YanickZengaffinen closed 5 months ago
1
Inner-Outer Loop

#13 YanickZengaffinen opened 6 months ago
0
Adversarial Setting

#12 YanickZengaffinen opened 6 months ago
2
Add function to draw MDPs + Fix transition and reward dimensions

#11 nilscrm closed 6 months ago
0
Gerstgrasser impl

#10 YanickZengaffinen closed 6 months ago
0
More complex Games

#9 YanickZengaffinen opened 6 months ago
0
How MBRL Approaches Fit Into Gerstgrasser Framework

#8 YanickZengaffinen opened 6 months ago
1
Add gitignore

#7 nilscrm closed 6 months ago
0
Comparison Against Literature

#6 YanickZengaffinen opened 6 months ago
0
Write Milestone

#5 nilscrm closed 6 months ago
1
Adapt simple MDP to use the oracles and followers algorithms for model based RL

#4 nilscrm closed 5 months ago
5
Make simple MDP and use Code from model based RL approach

#3 nilscrm closed 6 months ago
6
Make new environment for oracles and follower code

#2 nilscrm closed 6 months ago
1
Run Oracles and Followers paper code

#1 nilscrm closed 6 months ago
3