issues
search
mobeets
/
q-rnn
0
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
move to policy gradient approach?
#22
mobeets
opened
8 months ago
2
do not encode prev null action
#21
mobeets
opened
8 months ago
0
Beron with KL penalty
#20
mobeets
opened
8 months ago
7
Beron DA results
#19
mobeets
opened
8 months ago
2
Beron summary
#18
mobeets
opened
8 months ago
4
rllib/catch task: custom evaluation
#17
mobeets
opened
1 year ago
0
rllib: make GRU version of use_lstm
#16
mobeets
opened
1 year ago
0
delayed stateless cartpole
#15
mobeets
closed
1 year ago
5
Beron _sample_reward bug
#14
mobeets
closed
1 year ago
0
R2D2 using Ray
#13
mobeets
closed
1 year ago
1
Beron2022 timestep level
#12
mobeets
closed
1 year ago
2
Beron2022 reparameterization
#11
mobeets
closed
1 year ago
7
Why does Beron2022 have 4 fixed points?
#10
mobeets
closed
1 year ago
6
Signatures of other Beron2022 models
#9
mobeets
closed
1 year ago
0
Beron2022 stickiness
#8
mobeets
closed
1 year ago
5
Beron2022 stochasticity
#7
mobeets
closed
1 year ago
1
Beron2022 fixed points
#6
mobeets
closed
1 year ago
3
Beron2022 working example
#5
mobeets
closed
1 year ago
1
confirm belief update
#4
mobeets
closed
1 year ago
0
simpler task?
#3
mobeets
closed
1 year ago
0
todo: add previous action as a model input (onehot)
#2
mobeets
closed
1 year ago
0
does the Q function relate to beliefs?
#1
mobeets
closed
1 year ago
0