Harshit Sikchi
10 papers · 2020–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (14) πΊοΈ Taxonomy Completionist (10) π§ Keyword Pioneer π Conference Polyglot (5) π Academic Marathon (5)
π
Interdisciplinary Bridge
π
Century Club
(10)
β‘
Prolific Year
(5)
Conferences
ICLR (4)
CORL (3)
ICML (1)
NIPS (1)
RSS (1)
Top co-authors
Keywords
inverse reinforcement learning
(2)
sample efficiency
(1)
imitation learning
(1)
direct preference optimization
(1)
policy learning
(1)
online planning
(1)
trajectory optimization
(1)
reward function
(1)
reward hacking
(1)
language model
(1)
reward model
(1)
counterfactual reasoning
(1)
visual foundation model
(1)
autonomous navigation
(1)
actor critic
(1)
mapless navigation
(1)
state marginal matching
(1)
lookahead policy
(1)
off policy learning
(1)
reinforcement learning
(1)
Papers
CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance
RSS 2025
Proto Successor Measure: Representing the Behavior Space of an RL Agent
ICML 2025
An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning
ICLR 2025
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
NIPS 2024
Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
ICLR 2024
Score Models for Offline Goal-Conditioned Reinforcement Learning
ICLR 2024
A Dual Approach to Imitation Learning from Observations with Offline Datasets
CORL 2024
Dual RL: Unification and New Methods for Reinforcement and Imitation Learning
ICLR 2024
Learning Off-Policy with Online Planning
CORL 2021
f-IRL: Inverse Reinforcement Learning via State Marginal Matching
CORL 2020