issues
search
Kaixhin
/
Rainbow
Rainbow: Combining Improvements in Deep Reinforcement Learning
MIT License
1.59k
stars
284
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
float state?
#37
gorogm
closed
5 years ago
1
About Episodic Life at Test Phase
#36
zmonoid
closed
5 years ago
2
Use numpy arrays for speed
#35
Kaixhin
closed
5 years ago
3
Valid or Same padding in Conv2D?
#34
marintoro
closed
6 years ago
1
Improve the replay memory to avoid storing the autograd graphs in it
#33
deepbrain
closed
6 years ago
3
Same action in multi-agent environment
#32
lyp741
closed
6 years ago
1
Async queue for testing
#31
Kaixhin
opened
6 years ago
0
No ROM File specified or the ROM file was not found.
#29
zhan0903
closed
6 years ago
1
Ksg
#28
dldldlfma
closed
6 years ago
0
Add ability to resume training
#27
Kaixhin
opened
6 years ago
5
Performance of release v1.0 on Space Invaders
#26
marintoro
closed
6 years ago
13
Performance with QR prioritization on Space Invaders
#25
marintoro
closed
6 years ago
3
Updating Priorities with Importance Weighted Loss instead of TD-Error
#24
nasimrahaman
closed
6 years ago
1
Future improvements
#23
jaromiru
opened
6 years ago
4
Detach or not on Quantile loss?
#22
hohoCode
closed
6 years ago
0
Quick questions on the Quantile loss function
#21
hohoCode
closed
6 years ago
1
Asynchronous Multi-agent Rainbow
#20
marintoro
closed
6 years ago
1
Breakout
#19
Kaixhin
closed
6 years ago
1
TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'
#18
forhonourlx
closed
6 years ago
5
TypeError: stack(): argument 'tensors' (position 1) must be tuple of Tensors, not collections.deque
#17
forhonourlx
closed
6 years ago
7
Unit test Prioritised Experience Replay Memory
#16
Kaixhin
closed
6 years ago
5
Replicating DeepMind results
#15
Kaixhin
closed
6 years ago
24
Port alewrap
#14
Kaixhin
closed
6 years ago
0
Fix max in prioritised experience replay
#13
Kaixhin
closed
6 years ago
0
Testing should be not deterministic
#12
marintoro
closed
6 years ago
8
Handling of terminal state
#11
marintoro
closed
6 years ago
1
Is this code only implemented DQN version?
#10
JunningHuang
closed
6 years ago
1
Add environment.yml to make installation easier
#9
filipre
closed
6 years ago
1
Dimension problem in forward function in model.py
#8
marintoro
closed
6 years ago
1
Prioritised Experience Replay
#7
marintoro
closed
6 years ago
28
Add DeepMind wrappers for Gym environments
#6
Kaixhin
closed
6 years ago
0
Use preallocated tensor in replay memory
#5
Kaixhin
closed
6 years ago
1
Population Based Training of Neural Networks
#4
akaniklaus
closed
6 years ago
2
Memory
#3
Kaixhin
closed
6 years ago
0
Why didn't you reset the noise of target net?
#2
Halbmond
closed
7 years ago
3
Might also want to add uncertainty bellman equation
#1
ethancaballero
closed
6 years ago
2
Previous