Contents | Multiagent Reinforcement Learning toolbox |
asfq | Implements the adaptive state focus Q-learning algorithm |
asfq_init | Initializes the ASF-Q learning algorithm |
distrq | Implements the distributed Q-learning algorithm |
distrq_init | Initializes the distributed Q-learning algorithm |
fullstate_plainq | Implements the full-state plain Q-learning algorithm |
fullstate_plainq_init | Initializes the full-state plain Q-learning algorithm |
lrn | Implements the learning algorithm of the agent |
lrn_init | Template. Initializes the agent's learning behaviour |
minimaxq2 | Implements an alternate version of the minimax Q-learning algorithm |
minimaxq2_init | Initializes the minimax Q learning algorithm |
nillearn | Implements the nil (noop) learning algorithm |
nillearn_init | Nil learning behaviour initialization |
plainq | Implements the plain Q-learning algorithm |
plainq_init | Initializes the plain Q learning algorithm |
teamq | Implements the team Q-learning algorithm |
teamq_init | Initializes the team Q-learning algorithm |
wolfq | Implements the Win-or-Learn-Fast Policy Hill Climbing algorithm |
wolfq_init | Initialization of the WoLF-PHC learning algorithm |