Tom Bewley
Tom Bewley
J.P. Morgan AI Research
Verified email at - Homepage
Cited by
Cited by
TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments
T Bewley, J Lawry
🔍🤖 AAAI Conference on Artificial Intelligence, 2021
Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions
T Bewley, F Lecue
🔍🤖🏅 International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2021
Modelling Agent Policies with Interpretable Imitation Learning
T Bewley, J Lawry, A Richards
🔍 Trustworthy AI - Integrating Learning, Optimization and Reasoning, 180-186, 2021
Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning
J Early, T Bewley, C Evers, S Ramchurn
🔍🤖🏅 Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022
On the combination of gamification and crowd computation in industrial automation and robotics applications
T Bewley, M Liarokapis
2019 International Conference on Robotics and Automation (ICRA), 1955-1961, 2019
Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction
T Bewley, J Lawry, A Richards
🔍🤖 IJCAI Workshop on Explainable Artificial Intelligence (XAI), 2022
On Tour: Harnessing Social Tourism Data for City and Point of Interest Recommendation
T Bewley, I Palomares Carrascosa
1st International ‘Alan Turing’ Conference on Decision Support and …, 2019
Am I Building a White Box Agent or Interpreting a Black Box Agent?
T Bewley
🔍 arXiv preprint arXiv:2007.01187, 2020
Conservative World Models
S Jeen, T Bewley, JM Cullen
🤖 arXiv preprint arXiv:2309.15178, 2023
Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback
T Bewley, J Lawry, A Richards
🔍🤖🏅 AIAA SciTech Forum, 2023
Reward Learning with Trees: Methods and Evaluation
T Bewley, J Lawry, A Richards, R Craddock, I Henderson
🔍🤖🏅 arXiv preprint arXiv:2210.01007, 2022
The system can't perform the operation now. Try again later.
Articles 1–11