Oga-uct: On-the-go abstractions in uct
Recent work has begun exploring the value of domain abstractions in Monte-Carlo Tree
Search (MCTS) algorithms for probabilistic planning. These algorithms automatically …
Search (MCTS) algorithms for probabilistic planning. These algorithms automatically …
On lifted inference using neural embeddings
We present a dense representation for Markov Logic Networks (MLNs) called Obj2Vec that
encodes symmetries in the MLN structure. Identifying symmetries is a key challenge for lifted …
encodes symmetries in the MLN structure. Identifying symmetries is a key challenge for lifted …
Learning Path Constraints for UAV Autonomous Navigation under Uncertain GNSS Availability
This paper addresses a safe path planning problem for UAV urban navigation, under
uncertain GNSS availability. The problem can be modeled as a POMDP and solved with …
uncertain GNSS availability. The problem can be modeled as a POMDP and solved with …
[PDF][PDF] Conditional term equivalent symmetry breaking for SAT
Symmetry-breaking is a technique for efficiently solving SAT instances that contain high
degrees of symmetry among the variables of the instance. When satisfiability problems are …
degrees of symmetry among the variables of the instance. When satisfiability problems are …
[PDF][PDF] Learning Embeddings for Approximate Lifted Inference in MLNs
We present a dense representation for Markov Logic Networks (MLNs) that encodes
symmetries in the MLN. Such a representation is particularly important in the context of lifted …
symmetries in the MLN. Such a representation is particularly important in the context of lifted …
[PDF][PDF] Dissertation Abstract: Exploiting Symmetries in Sequential Decision Making under Uncertainty
A Anand - The 26th International Conference on …, 2016 - icaps16.icaps-conference.org
The problem of sequential decision making under uncertainty, often modeled as an MDP is
an important problem in planning and reinforcement learning communities. Traditional MDP …
an important problem in planning and reinforcement learning communities. Traditional MDP …