Steven James

11 papers · 2018–2024 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (5) 🗺️ Taxonomy Completionist (18) 💎 Century Club (11)

Conferences

ICLR (3) NIPS (3) ICML (2) IJCAI (2) CORL (1)

Top co-authors

Benjamin Rosman (7) Geraud Nangue Tasse (3) George Konidaris (3) Richard Klein (2) Devon Jarvis (2) Stefanie Tellex (1) Michael Beukman (1) Max Merlin (1) Sergio Orozco (1) Benjamin Van Niekerk (1)

Keywords

symbolic representation (2) policy learning (2) continual learning (1) transfer learning (1) benchmark dataset (1) hierarchical representation (1) boolean algebra (1) transition dynamics (1) latent variable (1) disentangled representation (1) value function (1) variational autoencoder (1) latent space (1) game ai (1) benchmark evaluation (1) evaluation benchmark (1) task planning (1) planning evaluation (1) game traversal (1) reinforcement learning (1)

Papers

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning ICLR 2024

GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps NIPS 2024

Overlooked Implications of the Reconstruction Loss for VAE Disentanglement IJCAI 2023

Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills CORL 2023

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies NIPS 2023

Autonomous Learning of Object-Centric Abstractions for High-Level Planning ICLR 2022

Generalisation in Lifelong Reinforcement Learning through Logical Composition ICLR 2022

Learning Portable Representations for High-Level Planning ICML 2020

A Boolean Task Algebra for Reinforcement Learning NIPS 2020

Composing Value Functions in Reinforcement Learning ICML 2019

Learning Portable Symbolic Representations IJCAI 2018