Paul Duckworth
7 papers · 2017–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🏃 Academic Marathon (8) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🐝 Cross-Pollinator (11)
🧭
Keyword Pioneer
🌍
Conference Polyglot
(5)
🏃
Academic Marathon
(8)
👑
Triple Crown
👥
Mega-Team
(24)
❓
The Questioner
Conferences
CORL (2)
ICLR (2)
ICML (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
model-based reinforcement learning
(2)
gaussian process
(2)
policy optimization
(1)
bayesian reinforcement learning
(1)
human activity recognition
(1)
expectation maximization
(1)
exploration-exploitation tradeoff
(1)
sequential monte carlo
(1)
activity recognition
(1)
tree search
(1)
expectation maximisation
(1)
mobile robot
(1)
temporal logic
(1)
monte carlo method
(1)
autonomous navigation
(1)
semi-markov decision process
(1)
natural language grounding
(1)
time-varying dynamics
(1)
autonomous robot
(1)
symbol grounding
(1)
Papers
Metalic: Meta-Learning In-Context with Protein Language Models
ICLR 2025
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
ICLR 2024
SPO: Sequential Monte Carlo Policy Optimisation
NIPS 2024
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
ICML 2024
Bayesian Reinforcement Learning for Single-Episode Missions in Partially Unknown Environments
CORL 2022
Time-Bounded Mission Planning in Time-Varying Domains with Semi-MDPs and Gaussian Processes
CORL 2020
Grounding of Human Environments and Activities for Autonomous Robots
IJCAI 2017