david-abel/simple_rl issues and pull requests

#67 - syntax fixes

Pull Request - State: closed - Opened by lucasgelfond 8 months ago - 1 comment

#66 - Refactoring

Pull Request - State: open - Opened by tosemml about 1 year ago

#65 - Error. How to solve this

Issue - State: open - Opened by mahmedpro over 1 year ago

#64 - Using Cleanup World

Issue - State: open - Opened by devram2000 almost 2 years ago

#63 - fix RMAX and speed it up with numpy

Pull Request - State: closed - Opened by zhouzypaul about 2 years ago

#62 - RMAX is slow and not implemented correctly

Issue - State: closed - Opened by zhouzypaul about 2 years ago - 1 comment

#61 - Utilize NumPy APIs to remove inefficient Python loops

Pull Request - State: closed - Opened by maldil over 2 years ago

#60 - Is Q Learning Softmax agent correctly implemented?

Issue - State: closed - Opened by RylanSchaeffer almost 3 years ago - 2 comments

#59 - Are policy gradient-based agents implemented?

Issue - State: closed - Opened by RylanSchaeffer almost 3 years ago - 8 comments

#58 - help

Issue - State: closed - Opened by aadeshnpn almost 4 years ago - 1 comment

#57 - AttributeError: type object 'RandomAgent' has no attribute 'q_func'

Issue - State: open - Opened by yyf17 almost 4 years ago

#56 - AttributeError: module 'time' has no attribute 'clock'

Issue - State: open - Opened by matthhong about 4 years ago - 2 comments

#55 - fix gridworld reset

Pull Request - State: closed - Opened by thisiscam about 4 years ago - 1 comment

#54 - *replaced references to deprecated time.clock() with time.time()

Pull Request - State: closed - Opened by AaEll about 4 years ago - 1 comment

#53 - minor bug fix - moved dot into string

Pull Request - State: closed - Opened by borea17 over 4 years ago

#52 - "a dead loop " def run_sample_trial(self, verbose=True): while not state.is_terminal():

Issue - State: open - Opened by oridong over 4 years ago

#51 - Gridworld Not Resetting

Issue - State: closed - Opened by dhalper1 over 4 years ago

#50 - brtdp_example.py

Issue - State: closed - Opened by oridong over 4 years ago - 2 comments

#49 - Switching goals

Issue - State: closed - Opened by bhairavmehta95 over 4 years ago - 2 comments

#48 - fixed issues with running on windows

Pull Request - State: closed - Opened by seand88 almost 5 years ago - 1 comment

#47 - Issues Running Example, open is not recognized as an internal or external command

Issue - State: closed - Opened by seand88 almost 5 years ago - 6 comments

#46 - POMDP related

Pull Request - State: closed - Opened by zkytony about 5 years ago - 2 comments

#45 - Fixes bug when FourRooms sizes are not divisible by 3

Pull Request - State: closed - Opened by camall3n about 5 years ago

#44 - Fixed a bug in value iteration.

Pull Request - State: closed - Opened by yrevar about 5 years ago

#43 - 'can't pickle dict_values objects' when running "belief_mdp_example.py" with Python 3

Issue - State: closed - Opened by zkytony about 5 years ago - 9 comments

#42 - Invalid policy visualization due to use of e-greedy action

Issue - State: closed - Opened by philwinder about 5 years ago - 2 comments

#41 - Invalid action values when using `visualize_learning`

Issue - State: closed - Opened by philwinder about 5 years ago - 2 comments

#40 - Forcing the use of the TkAgg Matplot lib backend prevents usage in notebooks

Issue - State: closed - Opened by philwinder over 5 years ago - 5 comments

#39 - Improved RMax + Visualizations

Pull Request - State: closed - Opened by NishanthJKumar over 5 years ago - 1 comment

#38 - Turn off print statement in ValueIteration.get_q_value()

Pull Request - State: closed - Opened by camall3n over 5 years ago - 1 comment

#37 - NavMDP: Support for custom obstacles.

Pull Request - State: closed - Opened by yrevar over 5 years ago

#36 - Visualizing GridWorld example

Issue - State: closed - Opened by apollokit over 5 years ago - 5 comments

#35 - Fixing a bug. Assertion failed when there were no probabilistic cells.

Pull Request - State: closed - Opened by yrevar over 5 years ago

#34 - Added initialization for rmax_agent in the second example

Pull Request - State: closed - Opened by melroderick over 5 years ago - 1 comment

#33 - Update imports for Python 3 compatibility

Pull Request - State: closed - Opened by KorlaMarch almost 6 years ago

#32 - adding cart-pole task

Pull Request - State: closed - Opened by paultouma almost 6 years ago - 1 comment

#31 - Updated eq in StateClass to return False on comparison to non-Sta…

Pull Request - State: closed - Opened by umbanhowar almost 6 years ago

#30 - Fixes reset_goals issue (failed when all navigation cells were manual…

Pull Request - State: closed - Opened by yrevar almost 6 years ago