issues
search
zuoxingdong
/
lagom
lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.
MIT License
373
stars
30
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Test PopArt in DDPG
#113
zuoxingdong
closed
5 years ago
0
remove StateValueHead
#112
zuoxingdong
closed
5 years ago
0
update run_experiment: timeit decorator
#111
zuoxingdong
closed
5 years ago
0
add timeit decorator
#110
zuoxingdong
closed
5 years ago
0
update timed: use better `perf_counter` and with a time stamp
#109
zuoxingdong
closed
5 years ago
0
update VPG/PPO
#108
zuoxingdong
closed
5 years ago
0
fix VecStandardize* and Module serialization
#107
zuoxingdong
closed
5 years ago
0
update VPG/PPO/DDPG
#106
zuoxingdong
closed
5 years ago
0
Benchmark lz4 for replay buffer compression
#105
zuoxingdong
closed
5 years ago
1
Update make_vec_env: seed observation/action spaces
#104
zuoxingdong
closed
5 years ago
0
well-tuned VPG/PPO
#103
zuoxingdong
closed
5 years ago
0
Add LazyFrames and memory efficient FrameStack
#102
zuoxingdong
closed
5 years ago
0
Rename ScaleImageObservation to ScaledFloatFrame
#101
zuoxingdong
closed
5 years ago
0
more updates
#100
zuoxingdong
closed
5 years ago
0
Update envs
#99
zuoxingdong
closed
5 years ago
0
fix AutoReset
#98
zuoxingdong
closed
5 years ago
0
update pyyaml: turn off sort_keys to preserve dict order
#97
zuoxingdong
closed
5 years ago
0
update requirements.txt
#96
zuoxingdong
closed
5 years ago
0
More updates
#95
zuoxingdong
closed
5 years ago
0
Remove mask support in geometric_cumsum, default to float64
#94
zuoxingdong
closed
5 years ago
0
Rename RunningAverage to PolyakAverage
#93
zuoxingdong
closed
5 years ago
0
Update EpisodeRunner: standardize terminal observation if wrapped
#92
zuoxingdong
closed
5 years ago
0
Re-implement with new TimeLimit concerns ?
#91
zuoxingdong
closed
5 years ago
0
Update lagom.envs
#90
zuoxingdong
closed
5 years ago
0
Update BaseAgent: add save/load
#89
zuoxingdong
closed
5 years ago
0
add DQN
#88
zuoxingdong
closed
5 years ago
0
Add dqn2
#87
zuoxingdong
closed
5 years ago
0
Refactor pg
#86
zuoxingdong
closed
5 years ago
0
add DQN to examples
#85
zuoxingdong
closed
5 years ago
0
Refactor pg
#84
zuoxingdong
closed
5 years ago
0
Simplify PG code
#83
zuoxingdong
closed
5 years ago
0
Update LinearSchedule
#82
zuoxingdong
closed
5 years ago
0
add MDNHead
#81
zuoxingdong
closed
5 years ago
0
add OpenAIES
#80
zuoxingdong
closed
5 years ago
0
add CEM
#79
zuoxingdong
closed
5 years ago
0
Update wrap_atari, add SignClipReward
#78
zuoxingdong
closed
5 years ago
0
Update envs: Add __len__, __getitem__ to VecEnv and VecEnvWrapper
#77
zuoxingdong
closed
5 years ago
0
remove BaseMaster, BaseWorker
#76
zuoxingdong
closed
5 years ago
0
Add CEM
#75
zuoxingdong
closed
5 years ago
0
Refactor ES
#74
zuoxingdong
closed
5 years ago
0
Update CloudpickleWrapper: support arguments and keyword arguments to…
#73
zuoxingdong
closed
5 years ago
0
remove lagom/memory
#72
zuoxingdong
closed
5 years ago
0
move lagom/agents to root
#71
zuoxingdong
closed
5 years ago
0
remove legacy
#70
zuoxingdong
closed
5 years ago
0
fix CI
#69
zuoxingdong
closed
5 years ago
0
fix CI
#68
zuoxingdong
closed
5 years ago
0
Update examples: PPO, VAE
#67
zuoxingdong
closed
5 years ago
0
Add OpenAI-ES
#66
zuoxingdong
closed
5 years ago
0
Breaking refactorings
#65
zuoxingdong
closed
5 years ago
0
Add tests for VecStandardizeObservation and VecStandardizeReward
#64
zuoxingdong
closed
5 years ago
0
Previous
Next