Tom Bewley - RankMe

25 papers A* 8A 1Journal 15Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Interpreting Language Reward Models via Contrastive Explanations. ICLR Junqi Jiang, Tom Bewley, Saumitra Mishra, Freddy Lécué, Manuela Veloso
2025	J	`jnl`	Representation Consistency for Accurate and Coherent LLM Answer Aggregation. CoRR Junqi Jiang, Tom Bewley, Salim I. Amoukou, Francesco Leofante, Antonio Rago, Saumitra Mishra, Francesca Toni
2025	A*	`conf`	To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models. ICML Anna Hedström, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso
2025	J	`jnl`	To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models. CoRR Anna Hedström, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso
2025	J	`jnl`	Zero-Shot Reinforcement Learning Under Partial Observability. CoRR Scott R. Jeen, Tom Bewley, Jonathan M. Cullen
2024	A*	`conf`	Counterfactual Metarules for Local and Global Recourse. ICML Tom Bewley, Salim I. Amoukou, Saumitra Mishra, Daniele Magazzeni, Manuela Veloso
2024	J	`jnl`	Counterfactual Metarules for Local and Global Recourse. CoRR Tom Bewley, Salim I. Amoukou, Saumitra Mishra, Daniele Magazzeni, Manuela Veloso
2024	J	`jnl`	Interpreting Language Reward Models via Contrastive Explanations. CoRR Junqi Jiang, Tom Bewley, Saumitra Mishra, Freddy Lécué, Manuela Veloso
2024	A*	`conf`	Sequential Harmful Shift Detection Without Labels. NeurIPS Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Freddy Lécué, Daniele Magazzeni, Manuela Veloso
2024	J	`jnl`	Sequential Harmful Shift Detection Without Labels. CoRR Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Freddy Lécué, Daniele Magazzeni, Manuela Veloso
2024	A*	`conf`	Zero-Shot Reinforcement Learning from Low Quality Data. NeurIPS Scott R. Jeen, Tom Bewley, Jonathan M. Cullen
2023	J	`jnl`	Conservative World Models. CoRR Scott R. Jeen, Tom Bewley, Jonathan M. Cullen
2023	J	`jnl`	Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback. CoRR Tom Bewley, Jonathan Lawry, Arthur Richards
2022	A	`conf`	Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions. AAMAS Tom Bewley, Freddy Lécué
2022	A*	`conf`	Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning. NeurIPS Joseph Early, Tom Bewley, Christine Evers, Sarvapali D. Ramchurn
2022	J	`jnl`	Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning. CoRR Joseph Early, Tom Bewley, Christine Evers, Sarvapali D. Ramchurn
2022	J	`jnl`	Reward Learning with Trees: Methods and Evaluation. CoRR Tom Bewley, Jonathan Lawry, Arthur Richards, Rachel Craddock, Ian Henderson
2022	J	`jnl`	Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction. CoRR Tom Bewley, Jonathan Lawry, Arthur Richards
2021	J	`jnl`	Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions. CoRR Tom Bewley, Freddy Lécué
2021	A*	`conf`	TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments. AAAI Tom Bewley, Jonathan Lawry
2020	J	`jnl`	Am I Building a White Box Agent or Interpreting a Black Box Agent? CoRR Tom Bewley
2020	—	`conf`	Modelling Agent Policies with Interpretable Imitation Learning. TAILOR Tom Bewley, Jonathan Lawry, Arthur Richards
2020	J	`jnl`	Modelling Agent Policies with Interpretable Imitation Learning. CoRR Tom Bewley, Jonathan Lawry, Arthur Richards
2020	J	`jnl`	TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments. CoRR Tom Bewley, Jonathan Lawry
2019	A*	`conf`	On The Combination of Gamification and Crowd Computation in Industrial Automation and Robotics Applications. ICRA Tom Bewley, Minas V. Liarokapis