Peter J Ramadge
5 papers · 2021–2022 · 2 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(14)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
safe reinforcement learning
(2)
language modeling
(1)
dynamics modeling
(1)
state estimation
(1)
constraint satisfaction
(1)
state representation
(1)
variance reduction
(1)
convergence guarantee
(1)
policy network
(1)
deep generative model
(1)
discrete latent variable
(1)
straight-through estimator
(1)
length extrapolation
(1)
constraint violation
(1)
finite-time convergence
(1)
reward optimization
(1)
physics constraint
(1)
kernel methods
(1)
multi-task benchmark
(1)
baseline policy
(1)
Papers
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
NeurIPS 2022
Learning Physics Constrained Dynamics Using Autoencoders
NeurIPS 2022
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
ICML 2022
Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies
ICML 2021
Safe Reinforcement Learning with Natural Language Constraints
NeurIPS 2021