nrontsis PILCO issues - Githubissues

nrontsis / PILCO

Bayesian Reinforcement Learning in Tensorflow

MIT License

314 stars 84 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Bugs in model update?

#63 fuku10 opened 2 years ago
1
Is squash_sin() right?

#62 fuku10 closed 2 years ago
1
NotImplementedError: Cannot convert a symbolic (graph mode) `DeferredTensor` to a numpy array.

#61 shubham83183 closed 1 year ago
2
AttributeError: 'Parameter' object has no attribute 'value'

#60 BlueShit-1120 opened 3 years ago
0
Performance issue in the definition of create_models, pilco/controllers.py(P1)

#59 DLPerf opened 3 years ago
0
Could you please share exact version of some dependency packages

#58 gitAugust opened 3 years ago
0
Speed up the policy optimization by @tf.function

#57 ikamensh opened 3 years ago
5
minor readability improvements

#56 ikamensh closed 3 years ago
1
Adds comments and some typing for readability

#55 ikamensh opened 3 years ago
0
How do you save your trained model?

#54 emsal0 opened 3 years ago
2
Allow PILCO to work with GPflow 2.1.0.

#53 emsal0 closed 3 years ago
1
installation: issue with gast, tensorflow

#52 emsal0 closed 3 years ago
6
Bump tensorflow from 2.1.0 to 2.1.2

#51 dependabot[bot] closed 4 years ago
0
What is the V for in the predict_given_factorizations

#50 qiaoting159753 opened 4 years ago
1
import set_trainable

#49 gpfins closed 4 years ago
0
fix: missing set_trainable import

#48 canbooo closed 4 years ago
0
[BUG] mountain_car.py fails due to missing import

#47 canbooo closed 4 years ago
0
Cholesky decomposition was not successful. The input might not be valid.

#46 Skylark0924 closed 4 years ago
2
Update to GPflow v2 and include safety extensions

#45 nrontsis closed 4 years ago
3
Cost for trajectory following

#44 Pengxiao-Gao opened 4 years ago
3
calculate_factorizations question

#43 NicolayP closed 4 years ago
1
SMGPR : the induced points are different for each model

#42 patxikuku opened 4 years ago
1
Gradient based policy optimisation.

#41 patxikuku closed 4 years ago
4
Reference for predicting with uncertain inputs with SMGPR

#40 powertj closed 4 years ago
1
Computation time for policy optimization

#39 dqxajzh opened 4 years ago
3
Error with cloudpickle

#38 sebelinho closed 4 years ago
0
Question about MGPR.

#37 leekwoon closed 4 years ago
0
Safety pr

#36 kyr-pol closed 4 years ago
4
Computation of cross-covariance of state and action

#35 dvtailor opened 5 years ago
0
Extra control dimension for varying target values

#34 ManuelM95 closed 5 years ago
4
Implement `predict_on_noisy_input` with MCMC in gpytorch

#33 jaztsong opened 5 years ago
7
Investigate performance of tf.linalg.det in predict_given_factorizations

#32 nrontsis opened 5 years ago
0
Cannot run on low-profile GPU

#31 jaztsong closed 5 years ago
10
Pr mountain car

#30 kyr-pol closed 4 years ago
1
PILCO for time delay

#29 iljastas closed 4 years ago
2
mujoco-py needed

#28 iljastas closed 5 years ago
1
Matrix contain inf or nan

#27 jastfkjg closed 5 years ago
2
pendulum_swing_up.py example doesn't solve the task

#26 JoeMWatson closed 4 years ago
3
Initialisation of ExponentialReward: eye(.) vs ones(.)

#25 ven-kyoshiro closed 5 years ago
4
Third output of function 'predict_given_factorizations' in mgpr.py

#24 jastfkjg closed 5 years ago
2
Added 3 more gym environment examples. Small changes to pilco.py, mgp…

#23 kyr-pol closed 5 years ago
5
bag fix and change to pybullet from mujoco

#22 ven-kyoshiro closed 5 years ago
1
Can it be applied to 'Pendulum-v0'?? && memory problem

#21 wonchul-kim closed 5 years ago
6
fixed #18: assigning model variable before calling

#20 zadiq closed 5 years ago
1
How dose it work?

#19 wonchul-kim closed 5 years ago
0
local variable 'model' referenced before assignment

#18 wonchul-kim closed 5 years ago
0
Utils pr

#17 kyr-pol opened 5 years ago
3
Add restarts for models and controllers, take care of tensorflow graph expanding - #13

#16 kyr-pol closed 5 years ago
2
Missing \delta^2 in C = max_action * tf.diag( tf.exp(-tf.diag_part(s)/2) * tf.cos(m))

#15 hejia-zhang closed 5 years ago
2
Use Matlab's implementation to train OpenAI gym tasks

#14 nrontsis opened 6 years ago
1