Satinder P. Singh

21 papers · 2008–2023 · 1 conference · across top CS/AI conferences

Achievements

+8 more ↓

🐝 Cross-Pollinator (14) 🏃 Academic Marathon (15) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (6)

🌈 Renaissance Researcher (6) 🗺️ Taxonomy Completionist (36) 🏠 Conference Loyalist (21) 🏆 Keyword Champion 📈 Trend Setter 🗃️ Keyword Collector (100) 💎 Century Club (21) ⚡ Prolific Year (6)

Conferences

NIPS (21)

Top co-authors

David Silver (6) Hado P van Hasselt (6) Tom Zahavy (5) Andre Barreto (5) Zhongwen Xu (4) Matteo Hessel (4) Junhyuk Oh (4) Richard L. Lewis (4) Christopher Grimm (3) Richard L Lewis (3)

Keywords

reinforcement learning (8) model-based reinforcement learning (3) value equivalence (3) policy gradient (3) value function (2) bellman operator (2) reward function (2) in-context learning (2) representation learning (2) auxiliary task (2) hierarchical reinforcement learning (2) optimal policy (2) unsupervised pretraining (1) state abstraction (1) fenchel duality (1) convex optimization (1) multi-task learning (1) sequence modeling (1) model combination (1) knowledge transfer (1)

Papers

Optimistic Meta-Gradients NIPS 2023 A Definition of Continual Reinforcement Learning NIPS 2023 Structured State Space Models for In-Context Reinforcement Learning NIPS 2023 Large Language Models can Implement Policy Iteration NIPS 2023 Combining Behaviors with the Successor Features Keyboard NIPS 2023 Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction NIPS 2022 Approximate Value Equivalence NIPS 2022 Palm up: Playing in the Latent Manifold for Unsupervised Pretraining NIPS 2022 Learning State Representations from Random Deep Action-conditional Predictions NIPS 2021 Proper Value Equivalence NIPS 2021 On the Expressivity of Markov Reward NIPS 2021 Reward is enough for convex MDPs NIPS 2021 Discovery of Options via Meta-Learned Subgoals NIPS 2021 Discovering Reinforcement Learning Algorithms NIPS 2020 A Self-Tuning Actor-Critic Algorithm NIPS 2020 Learning to Play No-Press Diplomacy with Best Response Policy Iteration NIPS 2020 Meta-Gradient Reinforcement Learning with an Objective Discovered Online NIPS 2020 On Efficiency in Hierarchical Reinforcement Learning NIPS 2020 The Value Equivalence Principle for Model-Based Reinforcement Learning NIPS 2020 Reward Design via Online Gradient Ascent NIPS 2010 Simple Local Models for Complex Dynamical Systems NIPS 2008