conftrace_
← Authors

Shangtong Zhang

27 papers · 2019–2026 · 6 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+13 more ↓ 🐝 Cross-Pollinator (13) 🌍 Conference Polyglot (6) 🧭 Keyword Pioneer πŸƒ Academic Marathon (6) πŸŒ‰ Interdisciplinary Bridge
πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (24) 🀝 Dynamic Duo (10) πŸ† Keyword Champion (3) 🌱 Topic Pioneer πŸ”¬ Deep Specialist (10) πŸ† Grand Slam 🧬 Topic Evolution πŸ”₯ Unstoppable (7) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (101) πŸ’Ž Century Club (26) ⚑ Prolific Year (8)

Conferences

AAAI (8) ICML (7) ICLR (4) JMLR (3) NIPS (3) IJCAI (2)

Top co-authors

Shimon Whiteson (10) Hengshuai Yao (4) Claire Chen (3) Shuze Liu (3) Bo Liu (3) Wendelin Boehmer (2) Remi Tachet des Combes (2) Shuze Daniel Liu (2) Romain Laroche (2) Ethan Blaser (2)

Keywords

reinforcement learning (8) off-policy learning (5) function approximation (5) temporal difference learning (4) stochastic approximation (3) deep reinforcement learning (3) finite sample analysis (3) off-policy evaluation (2) representation learning (2) deadly triad (2) target network (2) markovian noise (2) option framework (2) variance reduction (2) off-policy reinforcement learning (2) off-policy actor-critic (2) interpretable machine learning (1) convergence analysis (1) hierarchical learning (1) policy evaluation (1)

Papers

Asymptotic and Finite Sample Analysis of Nonexpansive Stochastic Approximations with Markovian Noise AAAI 2026 Revisiting a Design Choice in Gradient Temporal Difference Learning ICLR 2025 Efficient Multi-Policy Evaluation for Reinforcement Learning AAAI 2025 Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning ICLR 2025 Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning ICLR 2025 Doubly Optimal Policy Evaluation for Reinforcement Learning ICLR 2025 Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set ICML 2025 Counterfactual Explanations for Continuous Action Reinforcement Learning IJCAI 2025 The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise JMLR 2025 Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design ICML 2024 A New Challenge in Policy Evaluation AAAI 2023 On the Convergence of SARSA with Linear Function Approximation ICML 2023 Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch JMLR 2022 Learning Expected Emphatic Traces for Deep RL AAAI 2022 Truncated Emphatic Temporal Difference Methods for Prediction and Control JMLR 2022 Deep Residual Reinforcement Learning (Extended Abstract) IJCAI 2021 Average-Reward Off-Policy Policy Evaluation with Function Approximation ICML 2021 Breaking the Deadly Triad with a Target Network ICML 2021 Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning AAAI 2021 Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation ICML 2020 Learning Retrospective Knowledge with Reverse Reinforcement Learning NIPS 2020 Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards AAAI 2020 GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values ICML 2020 Generalized Off-Policy Actor-Critic NIPS 2019 DAC: The Double Actor-Critic Architecture for Learning Options NIPS 2019 ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search AAAI 2019 QUOTA: The Quantile Option Architecture for Reinforcement Learning AAAI 2019