mpatacchiola/dissecting-reinforcement-learning

Issues

• Part 3, TD(lambda): trace_matrix should be reset to zeroes at the beginning of each epoch

  #22 opened 6 months ago by johanwiden
  0

• Part.1 Modified Policy Iteration with Simplified Bellman Equation and Linear Algebra Policy Evaluation Infinite Loop

  #20 opened 2 years ago by CesarAndresRojas
  1

• mdp linear algebra approach cannot stop

  #6 opened 6 years ago by zdarktknight
  4

• Missing brackets

  #18 opened 4 years ago by DoDzilla-ai
  0

• Print statement causing issue in Python 3.x

  #15 opened 4 years ago by DoDzilla-ai
  0

• Two undefined variables

  #16 opened 4 years ago by DoDzilla-ai
  1

• The clean robot example on chapter 1 ?

  #14 opened 5 years ago by ngthanhtin
  2

• 11X11 grid

  #13 opened 5 years ago by Andlibmehndi
  2

• about greedy agent in multi-armed bandit

  #12 opened 5 years ago by ZichaoHuang
  2

• Looking forward to post #8

  #5 opened 5 years ago by BKJackson
  1

• adding optimal policy calculation in the value iteration algorithm

  #3 opened 6 years ago by ivan-v-kush
  2

• Problem in executing: "Montecarlo_control.py"

  #7 opened 6 years ago
  1

• typo in policy iteration algorithm on the site

  #2 opened 7 years ago by ivan-v-kush
  1

• Alternative to Numpy

  #1 opened 7 years ago by abencomo
  1