Skip to content

What is Reinforcement Learning?

Taxonomy of RL Methods

Multi-Armed Bandits

Markov Decision Processes

Dynamic Programming

Monte Carlo and Temporal-Difference Prediction

Sarsa and Q-Learning

Deep Q-Networks

DQN Improvements

Policy Gradient and REINFORCE

Actor-Critic, A2C and A3C

Off-Policy Policy-Based Framework

Dyna and Learned Models

Model Predictive Control

AlphaZero and MuZero

Imitation Learning

RLHF and Language Models

Goal-Conditioned RL

Advanced TopicsGoal-Conditioned RL

Goal-Conditioned RL

Hindsight Experience Replay and learning to reach arbitrary goals.

To be done soon

RLHF and Language Models

RLHF for autoregressive language models, from reward modeling and PPO to DPO and GRPO alternatives.

Multi-Agent RL

Cooperative and competitive multi-agent learning, MADDPG, QMIX, and communication.