Agent Components

• Actors
  • Off-Policy Actor
  • On-Policy Actor
  • Model-Based Actor
  • Actor Components
    • Action prob. distributions
    • Feature Extractors
    • Memory Networks
    • Noise
    • Reward Functions
    • World Models
• Algorithms
  • Off-policy
    • Double Deep Q-Learning (DDQN)
    • Deep Deterministic Policy Gradient (DDPG)
    • Twin Delayed Deep Deterministic (TD3)
    • Soft Actor Critic (SAC)
    • Maximum a Posteriori Policy Optimization (MPO)
  • On-policy
    • Advantage Actor Critic (A2C)
    • Proximal Policy Optimization (PPO)
    • Proximal Policy Optimization (PPO) with Random Network Distillation (RND)
  • Model-Based
    • Model Predictive Control (MPC) Random Shooting (RS)
    • Model Predictive Control (MPC) Cross-Entropy Method (CEM)
    • Model Predictive Control (MPC) Deep Dynamics Models (PDDM)
• Available Environments
• Environment Vectors
  • VecEnv
• Storage
  • Off-policy
    • Replay buffer
    • N-Step Replay Buffer
    • Prioritized Experience Replay Buffer
    • Emphasizing Recent Experience Replay Buffer (ERE)
    • Hindsight experience replay buffer (HER)
  • On-Policy
    • Vanilla On-Policy Buffer
    • Generalized Advantage Estimator (GAE) Buffer
    • V-trace Buffer
    • Proximal Policy Optimization with Demonstrations Buffer (PPOD)
  • Model-Based
    • ModelBased Replay Buffer