David Meger

22 papers · 2017–2024 · 8 conferences · across top CS/AI conferences

Achievements

+11 more ↓

🌍 Conference Polyglot (8) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🏃 Academic Marathon (7)

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (8) 🧬 Topic Evolution 🏆 Keyword Champion 🗃️ Keyword Collector (111) 🚀 Conference Pioneer 📈 Trend Setter 💎 Century Club (22) 🔥 Unstoppable (8) ❓ The Questioner

Conferences

NIPS (8) ICML (6) AAAI (3) CORL (1) JMLR (1) RSS (1) UAI (1) WACV (1)

Top co-authors

Scott Fujimoto (8) Doina Precup (8) Edward Smith (5) Sahand Rezaei-Shoshtari (5) Gregory Dudek (4) Francois R. Hogan (3) Marc G. Bellemare (2) Adriana Romero (2) Prakash Panangaden (2) Michael Jenkin (2)

Keywords

reinforcement learning (4) continuous control (4) value function (3) 3d reconstruction (3) tactile sensing (3) policy gradient (3) deep reinforcement learning (2) 3d object reconstruction (2) value function approximation (2) mesh reconstruction (2) multi-modal learning (2) transfer learning (1) robotic manipulation (1) ensemble learning (1) imitation learning (1) continual learning (1) offline reinforcement learning (1) epistemic uncertainty (1) state abstraction (1) uncertainty quantification (1)

Papers

Parseval Regularization for Continual Reinforcement Learning NIPS 2024 Policy Gradient Methods in the Presence of Symmetries and State Abstractions JMLR 2024 Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning NIPS 2024 Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models UAI 2024 For SALE: State-Action Representation Learning for Deep Reinforcement Learning NIPS 2023 Hypernetworks for Zero-Shot Transfer in Reinforcement Learning AAAI 2023 Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling AAAI 2023 Continuous MDP Homomorphisms and Homomorphic Policy Gradient NIPS 2022 Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning ICML 2022 Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error ICML 2022 Seeing Through Your Skin: Recognizing Objects With a Novel Visuotactile Sensor WACV 2021 Active 3D Shape Reconstruction from Vision and Touch NIPS 2021 Learning Intuitive Physics with Multimodal Generative Models AAAI 2021 A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation ICML 2021 An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay NIPS 2020 3D Shape Reconstruction from Vision and Touch NIPS 2020 Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles RSS 2020 Off-Policy Deep Reinforcement Learning without Exploration ICML 2019 GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects ICML 2019 Addressing Function Approximation Error in Actor-Critic Methods ICML 2018 Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation NIPS 2018 Improved Adversarial Systems for 3D Object Generation and Reconstruction CORL 2017