Contains Solutions of Lab assignments of Reinforcement Learning lab

see wiki for documentation and getting started.

  Probability And Statistics:
  Markov Chain, Sampling from Distributions,

  Multi Arm Bandits:
  Study of algorithms Like UCB, Thompson Sampling, Epsilon Greedy, Reinforce, Softmax for Multi Arm Bandits Problem with Bernoulli and Gaussian reward distribution.

  DP Methods for RL:
  Policy And Value Iteration for GridWorld

  Model Free RL Algorithms:
  MonteCarlo Control, SARSA, Q-Learning for MountainCar (Continious env), Taxi (discrete env).

  Linear Function Approximation and Policy Gradients:
  MonteCarlo Control, SARSA, Q-Learning with function approximation, DQN and A2C

  Literature survey, implementation and evaluation of Proximal Policy Optimization for various tasks.

  Other codes and assignments following various MOOCs.