AboudyKreidieh/h-baselines
A repository of high-performing hierarchical reinforcement learning models and algorithms.
PythonMIT
Issues
- 3
two problems (HAC and AntPush)
#226 opened by Hotwaterman - 0
action=nan problem
#250 opened by www2171668 - 2
Conflicting Dependencies
#245 opened by Markus28 - 0
Support for Discrete action spaces
#249 opened by MasonLilly - 3
Where is the benchmarking results?
#147 opened by chongyi-zheng - 2
What's the use of 'evaluate' in AntMaze env?
#160 opened by RushToNeverLand - 2
- 5
Visualize multiagent_traffic_light_grid
#129 opened by pengyuan-zhou - 0
Feudal Networks
#1 opened by AboudyKreidieh - 0
- 0
Documenting the README
#10 opened by AboudyKreidieh - 1
Data-Efficient HRL
#13 opened by fywu85 - 0
tests for replay buffers
#15 opened by AboudyKreidieh - 0
replace 8 with memory.trace_length
#16 opened by AboudyKreidieh - 0
modifications to training LSTMs
#17 opened by AboudyKreidieh - 0
- 0
separate actor and critic hidden_layers input
#19 opened by AboudyKreidieh - 0
- 0
fix hierarchical memory replay
#21 opened by AboudyKreidieh - 0
update logged names to include date
#22 opened by AboudyKreidieh - 0
Option-Critic
#12 opened by fywu85 - 0
DeepMind Locomotive
#11 opened by AboudyKreidieh - 0
Hierarchical Latent Space
#2 opened by AboudyKreidieh - 0
Model Abstractions
#5 opened by AboudyKreidieh - 0
Algortihm and importation abstractions
#6 opened by AboudyKreidieh - 0
Training Abstractions
#9 opened by AboudyKreidieh - 0
Unit testing Abstractions
#4 opened by AboudyKreidieh - 1
Swtiching Policies w/ SNN
#3 opened by AboudyKreidieh - 0
Installation and Conda Envs
#8 opened by AboudyKreidieh