Diana Borsa
10 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Cross-Pollinator (14) πΊοΈ Taxonomy Completionist (18) π Interdisciplinary Bridge
π
Conference Polyglot
(6)
π
Academic Marathon
(7)
π
Grand Slam
π
Century Club
(10)
π₯
Unstoppable
(6)
Conferences
ICML (3)
AISTATS (2)
NIPS (2)
AAAI (1)
ICLR (1)
JMLR (1)
Top co-authors
Research topics
Keywords
reinforcement learning
(4)
transfer learning
(3)
successor feature
(2)
value iteration
(2)
policy improvement
(2)
model-based reinforcement learning
(2)
deep reinforcement learning
(2)
reward function
(1)
state representation
(1)
policy gradient
(1)
bellman equation
(1)
importance sampling
(1)
policy evaluation
(1)
hierarchical reinforcement learning
(1)
off-policy learning
(1)
temporal-difference learning
(1)
epistemic uncertainty
(1)
value estimation
(1)
conditional value-at-risk
(1)
temporal difference learning
(1)
Papers
Optimizing Return Distributions with Distributional Dynamic Programming
JMLR 2025
A State Representation for Diminishing Rewards
NIPS 2023
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
ICML 2022
Generalised Policy Improvement with Geometric Policy Composition
ICML 2022
Expected Eligibility Traces
AAAI 2021
Conditional Importance Sampling for Off-Policy Learning
AISTATS 2020
Universal Successor Features Approximators
ICLR 2019
The Termination Critic
AISTATS 2019
The Option Keyboard: Combining Skills in Reinforcement Learning
NIPS 2019
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
ICML 2018