Module rl 

Reinforcement Learning module

Implements RL algorithms:

• Deep Q-Network (DQN)
• Policy Gradient (REINFORCE)
• Actor-Critic (A2C/A3C)
• Proximal Policy Optimization (PPO)
• Deep Deterministic Policy Gradient (DDPG)

Structs

ActorCriticAgent

Actor-Critic agent (A2C)

DQNAgent

Deep Q-Network (DQN) agent

Experience

PPOAgent

PPO (Proximal Policy Optimization) agent

PolicyNetwork

Policy network for policy gradient methods

QNetwork

Q-Network (simple MLP)

REINFORCEAgent

REINFORCE (Policy Gradient) agent

ReplayBuffer

Experience replay buffer for off-policy learning

ValueNetwork

Value network for critic