The following pages link to Tommi S. Jaakkola (Q1964685):
Displayed 22 items.
- Item:Q1964685 (redirect page) (← links)
- Convergence results for single-step on-policy reinforcement-learning algorithms (Q1568533) (← links)
- An introduction to variational methods for graphical models (Q1964686) (← links)
- (Q3295535) (← links)
- (Q3295536) (← links)
- (Q3295542) (← links)
- A New Class of Upper Bounds on the Log Partition Function (Q3547761) (← links)
- MAP Estimation Via Agreement on Trees: Message-Passing and Linear Programming (Q3547762) (← links)
- (Q4217792) (← links)
- (Q4217793) (← links)
- (Q4243444) (← links)
- (Q4250977) (← links)
- On the Convergence of Stochastic Iterative Dynamic Programming Algorithms (Q4323346) (← links)
- (Q4386941) (← links)
- (Q4410168) (← links)
- Modeling Persistent Trends in Distributions (Q4559709) (← links)
- Grounding Language for Transfer in Deep Reinforcement Learning (Q4611392) (← links)
- Tree-based reparameterization framework for analysis of sum-product and related algorithms (Q4680078) (← links)
- High Dimensional Inference With Random Maximum A-Posteriori Perturbations (Q5211460) (← links)
- Comparing the continuous representation of time-series expression profiles to identify differentially expressed genes (Q5460804) (← links)
- Research in Computational Molecular Biology (Q5706899) (← links)
- On Measure Concentration of Random Maximum A-Posteriori Perturbations (Q6245662) (← links)