Tom Bewley
7 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (4) πΊοΈ Taxonomy Completionist (14)
π
Conference Polyglot
(4)
π
Grand Slam
β
The Questioner
Conferences
NIPS (3)
ICML (2)
AAAI (1)
ICLR (1)
Top co-authors
Keywords
reinforcement learning
(2)
reward modeling
(1)
offline reinforcement learning
(1)
interpretable machine learning
(1)
multiple instance learning
(1)
covariate shift
(1)
value function
(1)
trajectory analysis
(1)
label shift
(1)
decision tree
(1)
autonomous agent
(1)
zero-shot reinforcement learning
(1)
successor feature
(1)
low quality datum
(1)
interpretable model
(1)
temporal dependency
(1)
state space
(1)
dataset quality
(1)
conservative algorithm
(1)
non-markovian reward
(1)
Papers
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
ICML 2025
Interpreting Language Reward Models via Contrastive Explanations
ICLR 2025
Zero-Shot Reinforcement Learning from Low Quality Data
NIPS 2024
Sequential Harmful Shift Detection Without Labels
NIPS 2024
Counterfactual Metarules for Local and Global Recourse
ICML 2024
Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning
NIPS 2022
TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments
AAAI 2021