Sanjiban Choudhury

32 papers · 2015–2025 · 7 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🌍 Conference Polyglot (7) 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (10)

🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (7) 🌍 Conference Polyglot (7) 👑 Triple Crown 🏆 Keyword Champion (2) 💎 Century Club (32) 🚀 Conference Pioneer ⚡ Prolific Year (6) 🗃️ Keyword Collector (83) 🔥 Unstoppable (9)

Conferences

ICML (8) ICLR (7) CORL (5) NIPS (5) RSS (4) IJCAI (2) NAACL (1)

Top co-authors

Gokul Swamy (8) Sebastian Scherer (5) Gonzalo Gonzalez-Pumariega (5) Siddhartha Srinivasa (4) Steven Wu (4) Drew Bagnell (4) Kushal Kedia (3) Prithwish Dan (3) Mohak Bhardwaj (3) Neha Sunkara (3)

Keywords

imitation learning (12) motion planning (5) edge evaluation (3) reinforcement learning (3) heuristic search (2) policy learning (2) collision-free path (2) continuous control (2) moment matching (2) behavioral cloning (2) online learning (2) inverse reinforcement learning (2) bayesian active learning (2) explanation generation (1) code generation (1) multi-task learning (1) sequential decision making (1) policy gradient (1) active learning (1) game theory (1)

Papers

Multi-Turn Code Generation Through Single-Step Rewards ICML 2025 X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real CORL 2025 Imitation Learning via Focused Satisficing IJCAI 2025 Efficient Imitation under Misspecification ICLR 2025 Robotouille: An Asynchronous Planning Benchmark for LLM Agents ICLR 2025 Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching ICLR 2025 Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Imitation Learning from a Single Temporally Misaligned Video ICML 2025 APRICOT: Active Preference Learning and Constraint-Aware Task Planning with LLMs CORL 2024 Hybrid Inverse Reinforcement Learning ICML 2024 UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations NAACL 2024 MOSAIC: Modular Foundation Models for Assistive and Interactive Cooking CORL 2024 Impossibly Good Experts and How to Follow Them ICLR 2023 Learning Shared Safety Constraints from Multi-task Demonstrations NIPS 2023 Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought NIPS 2023 The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms ICML 2023 ManiCast: Collaborative Manipulation with Cost-Aware Human Forecasting CORL 2023 Inverse Reinforcement Learning without Reinforcement Learning ICML 2023 Sequence Model Imitation Learning with Unobserved Contexts NIPS 2022 Towards Uniformly Superhuman Autonomy via Subdominance Minimization ICML 2022 Minimax Optimal Online Imitation Learning via Replay Estimation NIPS 2022 Causal Imitation Learning under Temporally Correlated Noise ICML 2022 Blending MPC & Value Function Approximation for Efficient Reinforcement Learning ICLR 2021 Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap ICML 2021 Learning from Interventions: Human-robot interaction as both explicit and implicit feedback RSS 2020 Bayesian Policy Optimization for Model Uncertainty ICLR 2019 Leveraging Experience in Lazy Search RSS 2019 Bayesian Active Edge Evaluation on Expensive Graphs IJCAI 2018 Near-Optimal Edge Evaluation in Explicit Generalized Binomial Graphs NIPS 2017 Learning Heuristic Search via Imitation CORL 2017 Adaptive Information Gathering via Imitation Learning RSS 2017 Theoretical Limits of Speed and Resolution for Kinodynamic Planning in a Poisson Forest RSS 2015