Pinned Repositories
astar_ros
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
bi-level-optimization-of-parameterized-reward-shaping
BIPARS is a weight reward shaping method, which is called bypass
CAI23sbP
CAI23sbP.github.io
DQN-pytorch
Deep Q-value Network by pytorch
GRU_AC
GRU-PPO for stable-baselines3.
RecurrentBC
Recurrent Behavior Cloning (with GRU)
RecurrentRLHF
Custom imitation library for making RecurrentReward model. I used GRU.
VGRNN
Variational Graph Recurrent Neural Networks - PyTorch
CAI23sbP's Repositories
CAI23sbP doesn’t have any repository yet.