3 votes
Accepted

Is Bayes optimal RL of a finite set of DFAs feasible?

Even determining whether there is a policy which always succeeds is NP-complete, by a reduction from constructing optimal decision trees (Hyafil and Rivest, Constructing Optimal Binary Decision Trees ...
zeb's user avatar
  • 376
2 votes

Polynomial convergence to optimal move of the UCT algorithm. Missing proof?

According to section 1.2 of https://arxiv.org/abs/1902.05213, there is not a published proof of the polynomial convergence rate, and even some of the proofs contained in [2] are not complete. Thus, it ...
1 vote
Accepted

Multi agent path following with collision avoidance with pre-determined path

In general, your problem is NP-hard, naturally (if you have arbitrarily many agents and an arbitrary arena, of course). Combining paths will naturally cause collisions (otherwise we wouldn't need ...
Shaull's user avatar
  • 5,571
1 vote

On-policy/Off-policy Offline/Online Evaluation: Which would be an example of Online Off-Policy Evaluation?

Online/Offline learning Whether your algorithm learns online or offline is governed by when the agent's experience is able to contribute to its learning. For example, consider value iteration ...
Dwait Bhatt's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible