conftrace_

Will Dabney

43 papers · 2017–2025 · 7 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

+14 more ↓

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

🐝 Cross-Pollinator (8) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (23) 👑 Triple Crown 🏆 Grand Slam 🔬 Deep Specialist (22) 🏆 Keyword Champion (3) 📈 Trend Setter 🚀 Conference Pioneer 🗃️ Keyword Collector (123) ⚡ Prolific Year (5) 💎 Century Club (43) 🔥 Unstoppable (9)

Conferences

ICML (18) NIPS (9) AISTATS (6) ICLR (6) JMLR (2) AAAI (1) IJCAI (1)

Top co-authors

Rémi Munos (23) Mark Rowland (21) Clare Lyle (12) Yunhao Tang (10) Georg Ostrovski (9) Andre Barreto (8) Anna Harutyunyan (8) David Abel (5) Nicolas Heess (5) Bernardo Avila Pires (5)

Research topics

Applications (1)

Keywords

deep reinforcement learning (12) reinforcement learning (10) distributional reinforcement learning (9) value function (6) return distribution (5) representation learning (5) off-policy learning (4) temporal difference learning (3) policy gradient (3) credit assignment (3) policy improvement (3) quantile regression (3) bellman equation (3) variance reduction (3) auxiliary task (3) spectral decomposition (2) transfer learning (2) temporal difference (2) policy evaluation (2) value estimation (2)

Papers

Optimizing Return Distributions with Distributional Dynamic Programming JMLR 2025 Discovering Symbolic Cognitive Models from Human and Animal Behavior ICML 2025 A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning AISTATS 2025 A Distributional Analogue to the Successor Representation ICML 2024 An Analysis of Quantile Temporal-Difference Learning JMLR 2024 Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model NIPS 2024 Normalization and effective learning rates in reinforcement learning NIPS 2024 Settling the Reward Hypothesis ICML 2023 Deep Reinforcement Learning with Plasticity Injection NIPS 2023 Understanding Self-Predictive Learning for Reinforcement Learning ICML 2023 The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation ICML 2023 Quantile Credit Assignment ICML 2023 Understanding Plasticity in Neural Networks ICML 2023 Bootstrapped Representations in Reinforcement Learning ICML 2023 Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition ICML 2023 On the Expressivity of Markov Reward (Extended Abstract) IJCAI 2022 The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning NIPS 2022 Understanding and Preventing Capacity Loss in Reinforcement Learning ICLR 2022 Generalised Policy Improvement with Geometric Policy Composition ICML 2022 Learning Dynamics and Generalization in Deep Reinforcement Learning ICML 2022 The Value-Improvement Path: Towards Better Representations for Reinforcement Learning AAAI 2021 The Difficulty of Passive Learning in Deep Reinforcement Learning NIPS 2021 On the Effect of Auxiliary Tasks on Representation Dynamics AISTATS 2021 Counterfactual Credit Assignment in Model-Free Reinforcement Learning ICML 2021 Revisiting Peng’s Q($λ$) for Modern Reinforcement Learning ICML 2021 On the Expressivity of Markov Reward NIPS 2021 Temporally-Extended ε-Greedy Exploration ICLR 2021 Revisiting Fundamentals of Experience Replay ICML 2020 Adaptive Trade-Offs in Off-Policy Learning AISTATS 2020 Conditional Importance Sampling for Off-Policy Learning AISTATS 2020 Fast Task Inference with Variational Intrinsic Successor Features ICLR 2020 Recurrent Experience Replay in Distributed Reinforcement Learning ICLR 2019 A Geometric Perspective on Optimal Representations for Reinforcement Learning NIPS 2019 Statistics and Samples in Distributional Reinforcement Learning ICML 2019 The Termination Critic AISTATS 2019 Hindsight Credit Assignment NIPS 2019 Distributed Distributional Deterministic Policy Gradients ICLR 2018 Autoregressive Quantile Networks for Generative Modeling ICML 2018 Implicit Quantile Networks for Distributional Reinforcement Learning ICML 2018 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning ICLR 2018 An Analysis of Categorical Distributional Reinforcement Learning AISTATS 2018 Successor Features for Transfer in Reinforcement Learning NIPS 2017 A Distributional Perspective on Reinforcement Learning ICML 2017