Philip Amortila
10 papers · 2020–2024 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (24) 👑 Triple Crown 🗃️ Keyword Collector (60)
🔥
Unstoppable · Bronze
📈
Trend Setter
💎
Century Club · Bronze
Top co-authors
Research topics
Keywords
markov decision process
(4)
reinforcement learning
(4)
online reinforcement learning
(3)
offline reinforcement learning
(2)
optimal policy
(2)
policy optimization
(2)
value function
(2)
empirical risk minimization
(1)
imitation learning
(1)
sample efficiency
(1)
policy learning
(1)
distributional reinforcement learning
(1)
sample complexity
(1)
value function approximation
(1)
convergence analysis
(1)
policy iteration
(1)
value iteration
(1)
function approximation
(1)
covariate shift
(1)
model misspecification
(1)
Papers
Harnessing Density Ratios for Online Reinforcement Learning
ICLR 2024
Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning
COLT 2024
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
NeurIPS 2024
Scalable Online Exploration via Coverability
ICML 2024
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation
ICML 2023
A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation
NeurIPS 2022
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions
ALT 2021
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function
COLT 2021
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
AISTATS 2020
Constrained Markov Decision Processes via Backward Value Functions
ICML 2020