issues
search
matomatical
/
jaxgmg
JAX-based environments and RL baselines for studying goal misgeneralisation.
MIT License
2
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Other regret estimators
#27
matomatical
closed
13 hours ago
0
Proxy regret estimation
#26
matomatical
closed
1 week ago
0
Move away from flax
#25
matomatical
opened
1 week ago
0
Type checking, testing, code formatting
#24
matomatical
opened
1 week ago
0
ACCEL mutators and training code refactor
#23
matomatical
closed
1 week ago
1
LSTM actually training
#22
matomatical
closed
3 weeks ago
0
New maze environment, cli/train refactor, fix lstm
#21
matomatical
closed
2 weeks ago
0
(Parallel) PLR with better metrics
#20
matomatical
closed
1 month ago
0
Refactor training level sets to new API supporting stateful curricula
#19
matomatical
closed
1 month ago
1
LSTM architectures + Support recurrent neural networks in the PPO algorithm.
#18
matomatical
closed
1 month ago
0
37 Implementation details of PPO
#17
matomatical
opened
1 month ago
3
Consider adding a no-op action to all environments.
#16
matomatical
opened
1 month ago
0
Evals refactor
#15
matomatical
closed
1 month ago
0
RL Baselines (other environments)
#14
matomatical
closed
1 month ago
1
Falling behind on documentation
#13
matomatical
opened
2 months ago
0
Heatmaps!
#12
matomatical
closed
2 months ago
0
Refactor solutions to LevelSolver class
#11
matomatical
closed
2 months ago
0
Resolution
#10
matomatical
closed
2 months ago
0
Sprites refactor
#9
matomatical
closed
2 months ago
0
RL Baseline (Cheese in the Corner)
#8
matomatical
closed
1 month ago
3
Possibility for generating invalid levels
#7
matomatical
opened
3 months ago
1
Add missing parsers
#6
matomatical
closed
3 months ago
0
"Follow me" environment
#5
matomatical
closed
3 months ago
0
Maze generator refactoring
#4
matomatical
closed
3 months ago
0
Lava land environment
#3
matomatical
closed
3 months ago
0
Cheese on a dish environment
#2
matomatical
closed
3 months ago
0
Perlin and fractal noise generation
#1
matomatical
closed
3 months ago
0