Rofunc RL

1. Rofunc RL Models:

   • QNetwork

   • ActorNetwork

   • CriticNetwork

2. Rofunc RL State Encoders:

   • CNN

   • ResNet

   • GCN

   • ViT

3. Rofunc RL Agents:

   • PPOAgent: Proximal Policy Optimization

   • TD3Agent: Twin Delayed Deep Deterministic Policy Gradient

   • SACAgent: Soft Actor-Critic

   • CQLAgent: Conservative Q-Learning

   • TD3BCAgent: TD3 with Behavior Cloning

   • DTransAgent: Decision Transformer

   • EDACAgent: Ensemble Distributional Actor-Critic

4. Rofunc RL Tasks:

   • FrankaCabinet

   • CURICabinet

5. Rofunc RL Trainers:

   • PPOTrainer

   • TD3Trainer

   • SACTrainer

   • CQLTrainer

   • TD3BCTrainer

   • DTransTrainer

   • EDACTrainer