Pseudocode

AlphaZero

Backpropagation

Conjugate Gradient Method

Constraint-Controlled Reinforcement Learning

Deep Q-learning

Deep Deterministic policy gradients (DDPG)

Deterministic policy gradients

Double Deep Q-learning

Dual Gradient Descent

Every-visit Monte Carlo prediction

First-visit Monte Carlo prediction

Implicit Q-Learning

\(n\)-step TD

One-step actor-critic

Policy iteration

PPO

Q-learning

REINFORCE

SARSA

Semi-gradient SARSA (episodic)

Semi-gradient TD(0)

Soft Actor-Critic (SAC)

Successor Features with Generalized Policy Improvement

Twin Delayed Deep Deterministic Policy Gradients (TD3)

TD(0)

TD(\(\lambda\))

Trust Region Policy Optimization (TRPO)

Value iteration