kshitija2 / Interactive-Multi-objective-Reinforcement-Learning

Multi-objective reinforcement learning deals with finding policies for tasks where there are multiple distinct criteria to optimize for. Since there may be trade-offs between the criteria, there does not necessarily exist a globally best policy; instead, the goal is to find Pareto optimal policies that are the best for certain preference functio…
20Updated 5 years ago

Related projects

Alternatives and complementary repositories for Interactive-Multi-objective-Reinforcement-Learning