Search results

Design of run loop and hooks

Status: Open.

#1090 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· johannes-fischer opened on Feb 3, 2025

Needless allocations in reward() and is_terminated() for

Status: Open.

#1080 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· hespanha opened on Aug 27, 2024

Wrong style for state report for TicTacToeEnv()

Status: Open.

#1079 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· hespanha opened on Aug 27, 2024

Does it allow defining an environment that has continuous action space? And how?

Status: Open.

#1078 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· WuSiren opened on Jul 14, 2024

It's not feasible to update the Q-based value agent in large steps for the RandomWalk1D() environment.

Status: Open.

#1068 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· Van314159 opened on Apr 16, 2024

Overspecific types in built-in policies and algorithms

Status: Open.

#1066 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· dharux opened on Apr 10, 2024

Update ReinforcementLearningAnIntroduction to be v0.11 compatible

Status: Open.

#1063 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· jeremiahpslewis opened on Mar 27, 2024

ReinforcementLearning.jl v0.12

v0.12

Status: Open.

#1061 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· jeremiahpslewis opened on Mar 26, 2024

·  

v0.12

Update Website, fix broken references / issues

bugSomething isn't workingSomething isn't working

Status: Open.

#1060 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· jeremiahpslewis opened on Mar 26, 2024

TicTacToeEnv allows illegal moves

bugSomething isn't workingSomething isn't working

Status: Open.

#1001 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· colintbowers opened on Nov 14, 2023

Missing features in RLCore

v0.12

Status: Open.

#961 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· HenriDeh opened on Aug 11, 2023

·  

v0.12

Improving Collaboration: Separate out the environment interface

v0.12

Status: Open.

#954 In JuliaReinforcementLearning/ReinforcementLearning.jl;

· zsunberg opened on Aug 9, 2023

·  

v0.12