zuoxingdong lagom issues

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

CVE-2007-4559 Patch

#214 TrellixVulnTeam opened 1 year ago
0
[setup.py] get_version: replace `importlib` with raw text scanning

#213 zuoxingdong opened 2 years ago
0
Use more fair RL evaluation metrics: IQM, Optimality Gap, Median, Mean

#212 zuoxingdong opened 3 years ago
0
Agent.choose_action: replace the mode string argument with internal self.training

#211 zuoxingdong opened 4 years ago
0
Agent constructor: replace environment object as spec object

#210 zuoxingdong opened 4 years ago
0
Extract independent snapshot functions for metrics: network, RL, experiment, statistics etc.

#209 zuoxingdong opened 4 years ago
0
Logging: convert loaded loggings entirely into pandas `DataFrame`

#208 zuoxingdong opened 4 years ago
0
Refactor Hyperparameter classes

#207 zuoxingdong opened 4 years ago
0
Support Python 3.8

#206 zuoxingdong opened 4 years ago
0
Migrate obs/reward normalization from env.wrappers into Agent itself

#205 zuoxingdong opened 4 years ago
0
Integrate Ray as an additional backend for parallel experiments

#204 zuoxingdong opened 4 years ago
0
Breaking changes: new experiment API

#203 zuoxingdong opened 4 years ago
0
Replace from_numpy/tensorify with as_tensor, remove tensorify

#202 zuoxingdong opened 4 years ago
0
Merge seed and device into config object

#201 zuoxingdong opened 4 years ago
0
Remove lz4 + atari-related when merged upstream to gym

#200 zuoxingdong closed 4 years ago
0
Numerical bug in RunningMeanVar

#199 zuoxingdong closed 5 years ago
0
make mujoco an optional dependence

#198 CarloLucibello closed 5 years ago
2
Update metric: independent of Trajectory object, but clear arguments …

#197 zuoxingdong closed 5 years ago
0
make baselines part of lagom

#196 CarloLucibello closed 5 years ago
7
Fix ES and PG methods to support discrete action space

#195 zuoxingdong closed 5 years ago
1
discrete RL examples

#194 CarloLucibello closed 5 years ago
1
the repo is very heavy

#193 CarloLucibello closed 5 years ago
5
VAE Experiment uses old run_experiments function

#192 albertwujj opened 5 years ago
4
Best way to test an agent ?

#191 MoMe36 opened 5 years ago
4
update new loggings for CMA-ES

#190 zuoxingdong closed 5 years ago
0
improve CI: use conda as much as possible for MKL optimization etc.

#189 zuoxingdong closed 5 years ago
0
minor update

#188 zuoxingdong closed 5 years ago
0
add SAC

#187 zuoxingdong closed 5 years ago
0
minor update to TD3

#186 zuoxingdong closed 5 years ago
0
minor update to DDPG

#185 zuoxingdong closed 5 years ago
0
update run_experiment

#184 zuoxingdong closed 5 years ago
0
sync TD3 to latest refactoring

#183 zuoxingdong closed 5 years ago
0
update run_experiment: more resources loggings

#182 zuoxingdong closed 5 years ago
0
sync SAC to latest refactoring [ongoing]

#181 zuoxingdong closed 5 years ago
0
sync DDPG to latest refactoring

#180 zuoxingdong closed 5 years ago
0
update logs to VPG/PPO

#179 zuoxingdong closed 5 years ago
0
Update transform: add SegmentTree/SumTree/MinTree

#178 zuoxingdong closed 5 years ago
0
update logs for VPG/PPO

#177 zuoxingdong closed 5 years ago
0
Code Stability

#176 rachel-1 closed 5 years ago
5
Support __getattr__ to VecEnv like Env in gym

#175 zuoxingdong closed 5 years ago
0
update ES baselines

#174 zuoxingdong closed 5 years ago
0
update run_experiment: support run serially

#173 zuoxingdong closed 5 years ago
0
update CEM

#172 zuoxingdong closed 5 years ago
0
update PPO

#171 zuoxingdong closed 5 years ago
0
update VPG

#170 zuoxingdong closed 5 years ago
0
newly implement run_experiment

#169 zuoxingdong closed 5 years ago
0
Update VPG

#168 zuoxingdong closed 5 years ago
0
update runner: adapt to VecStepInfo

#167 zuoxingdong closed 5 years ago
0
fix CI

#166 zuoxingdong closed 5 years ago
0
revert gym in requirements.txt when latest TimeLimit updated by gym

#165 zuoxingdong closed 5 years ago
0