Brett Daley

5 papers · 2019–2024 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICML (2) CoRL (1) NeurIPS (1) UAI (1)

Top co-authors

Christopher Amato (4) Martha White (2) Marlos C. Machado (2) Robert Platt (1) Xinchao Song (1) Andrea Baisero (1) Hai Nguyen (1)

Research topics

Reinforcement Learning (4) Methods (4) Machine Learning (3) Artificial Intelligence (1) Deep Learning (1) Applications (1) Core AI (1) Core Methods (1) Learning Types (1) Optimization & Theory (1) Techniques (1)

Keywords

partial observability (2) eligibility trace (2) temporal difference learning (2) deep reinforcement learning (2) dynamic programming (1) policy iteration (1) variance reduction (1) off-policy learning (1) temporal difference (1) credit assignment (1) information gathering (1) experience replay (1) auxiliary loss (1) multi-step return (1) n-step return (1) lambda return (1) belief state reconstruction (1) history summarization (1) compound returns (1) minibatched experience replay (1)

Papers

Averaging n-step Returns Reduces Variance in Reinforcement Learning ICML 2024 Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning ICML 2023 Asymmetric DQN for partially observable reinforcement learning UAI 2022 Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability CoRL 2020 Reconciling λ-Returns with Experience Replay NeurIPS 2019