RLE-Foundation/RLeXplore
RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).
Jupyter NotebookMIT
Issues
- 2
Problems with action spaces > 1 in icm
#21 opened by Croip3 - 2
atari enviroment error
#20 opened by haneenhassen - 1
code for paper
#19 opened by hlsafin - 1
Deterministic behavior in evaluation
#18 opened by edofazza - 9
RLeXplore with Stable Baseline3 example issue
#16 opened by edofazza - 2
State of this project?
#12 opened by dominikonysz - 1
The modules cannot be called!
#17 opened by amirmmi - 1
OffPolicyAlgorithm and obs dict
#15 opened by hpugq - 2
- 3
Is this project suitable for our own environment?
#14 opened by yq60523 - 2
NGU - need to understand this line
#8 opened by emrul - 3
RIDE Code issues
#5 opened by yZ265519 - 2
NGU implementation
#4 opened by TakieddineSOUALHI - 1
Intrinsic reward
#10 opened by mchivuku - 1
Training in custom environments
#6 opened by priyankamandikal - 1
Correct usage with SB3 / Callbacks?
#3 opened by emrul - 2
Project Page Stable Baselines3
#2 opened by araffin - 1
Save and load models
#1 opened by lamare3423