Homepage
Open in app
Sign in
Get started
Neurosapiens
🧠 Deep learning
📷 Vision
✍🏼 NLP
💻 Programming
🥇🇰aggle
🤖 Reinforcement Learning
Reinforcement Learning
Part 1: Foundations
1. Introduction
1. Introduction
Agent, Reward, Discounted return
Javier Abellán Abenza
Jan 1, 2019
2. Dynamic programming
2. Dynamic programming
Bellman equation, Policy Evaluation, Policy Improvement, Policy Iteration Value Iteration
Javier Abellán Abenza
Jan 4, 2019
3. Monte Carlo Methods
3. Monte Carlo Methods
Monte Carlo prediction and control methods. Greedy and epsilon-greedy policies. Exploration-Exploitation Dilemma.
Javier Abellán Abenza
Jan 5, 2019
4. Temporal-Difference Learning
4. Temporal-Difference Learning
Learn the difference between the Sarsa, Q-Learning, and Expected Sarsa algorithms.
Javier Abellán Abenza
Jan 5, 2019
5. RL in Continuous Spaces
5. RL in Continuous Spaces
Learn how to adapt traditional algorithms to work with continuous spaces. Discretization. Tile Coding
Javier Abellán Abenza
Jan 5, 2019
Deep Reinforcement Learning
7. Value Based Methods
7. Value Based Methods
Deep Q-Network (DQN), along with Double-DQN, Dueling-DQN, and Prioritized Replay.
Javier Abellán Abenza
Jan 5, 2019
8. Policy Based Methods
8. Policy Based Methods
Evolutionary algorithms, stochastic policy search, and REINFORCE algorithm.
Javier Abellán Abenza
Jan 5, 2019
9. Policy Gradient Methods
9. Policy Gradient Methods
Generalized Advantage Estimation (GAE), Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO).
Javier Abellán Abenza
Jan 5, 2019
10. Actor Critic Methods
10. Actor Critic Methods
Deep Deterministic Policy Gradients (DDPG)
Javier Abellán Abenza
Jan 5, 2019
11. Multi Agent RL
11. Multi Agent RL
Monte Carlo Tree Search (MCTS)
Javier Abellán Abenza
Jan 5, 2019
Index
Index
Reinforcement Learning index
Javier Abellán Abenza
Dec 31, 2018
About Neurosapiens
Latest Stories
Archive
About Medium
Terms
Privacy
Teams