Mehdi Fatemi
11 papers · 2017–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🧭 Keyword Pioneer 🐝 Cross-Pollinator (12) 🌍 Conference Polyglot (3) 🏃 Academic Marathon (7) 🌈 Renaissance Researcher (5)
🌍
Conference Polyglot
(3)
🏃
Academic Marathon
(7)
🐝
Cross-Pollinator
(12)
👑
Triple Crown
💎
Century Club
(11)
📈
Trend Setter
Conferences
ICLR (4)
NIPS (4)
ICML (3)
Top co-authors
Keywords
value function
(3)
reinforcement learning
(3)
policy optimization
(2)
dead-end state
(2)
discount factor
(1)
value estimation
(1)
deep neural network
(1)
sparse reward
(1)
reward decomposition
(1)
abstractive summarization
(1)
secure exploration
(1)
bridge effect
(1)
large language model
(1)
shortest-path constraint
(1)
risk identification
(1)
approximate representation
(1)
intensive care unit
(1)
trajectory exploration
(1)
action gap
(1)
logarithmic mapping
(1)
Papers
Successor Features for Efficient Multi-Subject Controlled Text Generation
ICML 2024
A Dynamical View of the Question of Why
ICLR 2024
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
NIPS 2024
Systematic Rectification of Language Models via Dead-end Analysis
ICLR 2023
Orchestrated Value Mapping for Reinforcement Learning
ICLR 2022
Learning to Represent Action Values as a Hypergraph on the Action Vertices
ICLR 2021
Medical Dead-ends and Learning to Identify High-Risk States and Treatments
NIPS 2021
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
ICML 2021
Dead-ends and Secure Exploration in Reinforcement Learning
ICML 2019
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
NIPS 2019
Hybrid Reward Architecture for Reinforcement Learning
NIPS 2017