History

GitHub Log

  • Mar 06, 2019
    • (by: sonofeft)
      • Added Figure 9.2 code
  • Mar 04, 2019
    • (by: sonofeft)
      • Added Fig 9.2 TD(0) semi-gradient and docs
      • Added Figure 9.1 to docs
      • made Figure 9.1
  • Mar 03, 2019
    • (by: sonofeft)
      • refactored some semi-gradient SARSA
  • Feb 28, 2019
    • (by: sonofeft)
      • created SA_SemiGradAgent with sarsa and qlearning
        Added example from LazyProgrammer Intro RL class
  • Feb 27, 2019
    • (by: sonofeft)
      • added set_half_life_for_N_episodes to Alpha and EpsilonGreedy objects
      • Built first version of linear function approximator agent
  • Feb 24, 2019
    • (by: sonofeft)
      • some updates to tkinter grid world
      • moved mdp_pickle files to User HOME directory
  • Feb 23, 2019
    • (by: sonofeft)
      • Some history update
      • Added Priority Sweep Logic
  • Feb 21, 2019
    • (by: sonofeft)
      • added named_s_hash, dyna_grid_xN, priority_queue, some TODO
  • Feb 20, 2019
    • (by: sonofeft)
      • single line description in setup.py required
      • fixed pickle file inclusion in PyPI
      • First Git Commit
  • 2019-02-19 23:35 Charlie Taylor
    • added more chapter 8 figures to docs
  • 2019-02-19 02:02 Charlie Taylor
    • got Dyna-Q to work
  • 2019-02-14 16:39 Charlie Taylor
    • clarified policy evaluation for nsteps
  • 2019-02-14 12:53 Charlie Taylor
    • ran all the __name__==__main__ tests
  • 2019-02-14 12:51 Charlie Taylor
    • rewrote nstep_walker
  • 2019-02-13 15:36 Charlie Taylor
    • added SARSA to n-step walker
  • 2019-02-11 09:29 Charlie Taylor
    • updates to chapter 6 docs
  • 2019-02-11 01:18 Charlie Taylor
    • lots of cleanup and windy gridworld docs
  • 2019-02-10 22:17 Charlie Taylor
    • cleaned up loop_counter
  • 2019-02-07 17:49 Charlie Taylor
    • finished first draft of chapter 5 docs
  • 2019-02-07 03:33 Charlie Taylor
    • added to chapter 5, MC docs page
  • 2019-02-06 16:02 Charlie Taylor
    • got rid of loop_counter in MC funcs
  • 2019-02-06 10:27 Charlie Taylor
    • added randomized iteration to MC functions
  • 2019-02-06 01:49 Charlie Taylor
    • MC routines needed max_num_episodes clarified
  • 2019-02-06 01:01 Charlie Taylor
    • working on docs and policy diagram
  • 2019-02-05 01:48 Charlie Taylor
    • added sample simulation
  • 2019-02-04 21:39 Charlie Taylor
    • found correction in Zhang car rental
  • 2019-02-03 10:49 Charlie Taylor
    • more docs added
  • 2019-02-02 23:05 Charlie Taylor
    • added arrows to policy diagram
  • 2019-02-02 17:47 Charlie Taylor
    • moved GenericLayout up into EnvBaseline call for most mdp
  • 2019-02-02 15:03 Charlie Taylor
    • created sample mdp for docs
  • 2019-02-01 02:05 Charlie Taylor
    • started MC docs and added blackjack
  • 2019-01-31 10:06 Charlie Taylor
    • added td_funcs and removed state_value_alpha_coll
  • 2019-01-31 02:10 Charlie Taylor
    • doc updates
  • 2019-01-31 00:53 Charlie Taylor
    • added documentation for chap 3 and 4
  • 2019-01-30 08:52 Charlie Taylor
    • a bunch of reorganizing
  • 2019-01-30 02:00 Charlie Taylor
    • migrating examples into IntroRL
  • 2019-01-29 23:29 Charlie Taylor
    • added some defined MDP environments
  • 2019-01-29 15:03 Charlie Taylor
    • Initial Empty Project
  • Jan 29, 2019
    • (by: sonofeft)
      • First Created IntroRL with PyHatch

PyHatch

IntroRL Framework Created by: PyHatch on Jan 29, 2019

(PyHatch Initializes Files And Directory Structures For New Python Projects.)

See PyHatch Docs at: http://pyhatch.readthedocs.org/en/latest/