reinforcement learning workshop

reinforcement learning workshop

1. resources

   • video
     • kjfalkdjf asdfasdf 
   • book
   • slide
   • code snip
   • github summary
     • Lectures [UCL] COMPM050/COMPGI13 Reinforcement Learning by David Silver [UC Berkeley] CS188 Artificial Intelligence by Pieter Abbeel Lecture 8: Markov Decision Processes 1 Lecture 9: Markov Decision Processes 2 Lecture 10: Reinforcement Learning 1 Lecture 11: Reinforcement Learning 2 [Udacity (Georgia Tech.)] CS7642 Reinforcement Learning [Stanford] CS229 Machine Learning - Lecture 16: Reinforcement Learning by Andrew Ng [UC Berkeley] Deep RL Bootcamp [UC Berkeley] CS294 Deep Reinforcement Learning by John Schulman and Pieter Abbeel [CMU] 10703: Deep Reinforcement Learning and Control, Spring 2017 [MIT] 6.S094: Deep Learning for Self-Driving Cars Lecture 2: Deep Reinforcement Learning for Motion Planning [Siraj Raval]: Introduction to AI for Video Games (Reinforcement Learning Video Series) [Introduction to AI for video games] (https://youtu.be/i_McNBDP9Qs) [Monte Carlo Prediction] (https://youtu.be/-YpalutQCKw) [Q learning explained] (https://youtu.be/aCEvtRtNO-M) [Solving the basic g

2. traditional content

   • tabular solution method
     • basic root of RL (model based)
       • MDP
         • 1.policy PI and value f(x),v(s), Q(s,a)
         • 2.bellman equation
       • Dynamic Process
         • 1.iterative policy evaluation
           • 2.policy improvement
             • 3.policy iteration
               • 4. value iteration
     • model free sampler
       • Monte carlo
         • 1. MC prediction and control methods
         • 2. greedy and epsilon-greedy policies
         • 3. Exploration-Exploitation Dilemma
       • temporal Difference
         • 1. sarsa small kid
         • 2. Q-learning big kid
           • Expected Sarsa algorithms
       • N-step Bootsrappin
         • TD(0),,,,TD(Lmda)
       • planing and learning with tabular methods
   • approximate solution method
     • on-policy
       • on-policy prediction with Approximation
       • on-policy control
     • off-policy
     • eligible trace
     • Policy Gradient Method
       • PG theorem
       • MC policy Gradient
       • Actor-Critic, A2C, A3c

3. Core concept compare

   • online vs offline
   • on-policy vs off-policy
   • model-based vs model free vs

4. Programing Environment

   • Gym

5. value-based method

6. Policy-based method

7. basic key words

   • states and observations,
   • action spaces
     • continue vs discrete
   • policies PI
   • trajectories
   • different formulations of return
   • the RL optimization problem
   • value functions.
   • environment
   • agent

Imagens e arquivos do mapa