S. Dumančić
49 records found
1
LeanSolver: Solving theorems through Large Language Models and Search
Improving Theorem Proving with Proof Assistants and Sequential Monte Carlo in Large Language Models
Large Language Models on their own are known to be ...
Program Synthesis from Rewards using Probe and FrAngel
Impact of Exploration-Exploitation Configurations on Probe and FrAngel in Minecraft
We explore existing synthesizer ...
Program Synthesis from Game Rewards Using FrAngel
Finding Complex Subprograms for Solving Minecraft
Scaling Program Synthesis
Combining Programs Learned on Subsets of Examples
Efficient Program Synthesis via Anti-Unification
Enhancing Domain-Specific Language-Based Synthesis by Identifying and Utilizing Common Patterns
Improving Enumerative Program Synthesis Performance by Extending Grammar from Solutions to Simpler Synthesis Problems
How can such approach be implemented in a synthesis system that cannot benefit from in-advance refinement of the synthesis algorithm parameters
Program Synthesis from Rewards with Probe
Adjusting Probe to Increase Exploration When Synthesising Programs from Rewards in Minecraft
Reward Based Program Synthesis for Minecraft
Adapting Program Synthesizers for Reward Evaluation and Leveraging Discovered Programs
Re-evaluating the Full Landmark Extraction Algorithm
A Performance Analysis of FULL
Landmarks in Planning
Using landmarks as Intermediary Golas or as a Pseudo-Heuristic
Reproducing the concept of ordered landmarks in planning
The effect of ordered landmarks on plan length in forward search