issues
search
kengz
/
SLM-Lab
Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
https://slm-lab.gitbook.io/slm-lab/
MIT License
1.25k
stars
264
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
dqn pong specs
#363
lgraesser
closed
5 years ago
0
Fix SIL breakage, still untested
#362
kengz
closed
5 years ago
0
enable PPO time horizon param
#361
kengz
closed
5 years ago
0
Video recording
#360
colllin
opened
5 years ago
8
Rewrite job scheduler using Ray
#359
kengz
closed
5 years ago
0
Organize all spec files
#358
kengz
closed
5 years ago
0
cleanup README; register package
#357
kengz
closed
5 years ago
0
REINFORCE center mean returns; remove a, e idx from Agent, Env
#356
kengz
closed
5 years ago
0
update Docker, Conda
#355
kengz
closed
5 years ago
0
fix lr spec to use frame
#354
kengz
closed
5 years ago
0
format README
#353
kengz
closed
5 years ago
0
v4.0.0 prerelease merge: Algorithm Benchmark, Analysis, API simplification
#352
kengz
closed
5 years ago
0
update v4 README; rename config to job
#351
kengz
closed
5 years ago
0
Update Ray search
#350
kengz
closed
5 years ago
0
generate random baseline for all envs
#349
kengz
closed
5 years ago
0
Remove Space code for major simplification
#348
kengz
closed
5 years ago
0
Rework analysis
#347
kengz
closed
5 years ago
0
Add full-Atari specs
#346
kengz
closed
5 years ago
0
generate random baseline
#345
kengz
closed
5 years ago
0
Fix eval modes
#344
kengz
closed
5 years ago
0
Fix a3c spec with num_envs
#343
kengz
closed
5 years ago
0
Add NormalizeStateEnv wrapper
#342
kengz
closed
5 years ago
0
add A3C shared GPU specs
#341
kengz
closed
5 years ago
0
A3C distributed modes
#340
kengz
closed
5 years ago
0
Refactor net interface and optim
#339
kengz
closed
5 years ago
0
update gym and plotly install, update a3c spec
#338
kengz
closed
5 years ago
0
guard hogwild distributed spec
#337
kengz
closed
5 years ago
0
update a3c specs
#336
kengz
closed
5 years ago
0
parametrize spec, replace InfoSpace
#335
kengz
closed
5 years ago
0
update continuous env spec files
#334
kengz
closed
5 years ago
0
Full benchmark specs
#333
kengz
closed
5 years ago
0
allow usage of different spec scheduler file
#332
kengz
closed
5 years ago
0
Reward preprocessing in wrapper; retire Atari-specific memories
#331
kengz
closed
5 years ago
0
Unify preprocessing, retire some memory classes
#330
kengz
closed
5 years ago
0
Count gradient steps automatically in clock
#329
kengz
closed
5 years ago
0
Speedup PER
#328
kengz
closed
5 years ago
0
Add PPO minibatch sampling
#327
kengz
closed
5 years ago
0
Cast numpy before pytorch for 2% speed gain
#326
kengz
closed
5 years ago
0
Fixed docker image build error
#325
Rahim16
closed
5 years ago
1
Multi-continuous actions with Roboschool
#324
kengz
closed
5 years ago
0
fix vec total rewards, vector framestack
#323
kengz
closed
5 years ago
0
Safe Q-learning refactor
#322
kengz
closed
5 years ago
0
Multi-continuous action spaces
#321
lgraesser
closed
5 years ago
0
Generalize Q-learning algorithms for vector environments
#320
kengz
closed
5 years ago
0
Fix reward reset
#319
kengz
closed
5 years ago
0
Policy gradient specs
#318
lgraesser
closed
5 years ago
1
cleanup logging; lower-bound fitness
#317
kengz
closed
5 years ago
0
Cleanup env, commit init_fn logic
#316
kengz
closed
5 years ago
0
commit working A2C vec env Pong
#315
kengz
closed
5 years ago
0
Policy util rework
#314
kengz
closed
5 years ago
0
Previous
Next