conftrace_

Philip J Ball

2 papers · 2021–2022 · 1 venue · 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 ↓

🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

Top co-authors

Stephen Roberts (2) Jack Parker-Holder (1) Oya Celiktutan (1) Edoardo Cetin (1) Cong Lu (1)

Research topics

Machine Learning (2) Reinforcement Learning (2) Methods (2) Learning Types (1) Optimization & Theory (1)

Keywords

deep reinforcement learning (1) zero-shot learning (1) temporal difference learning (1) offline reinforcement learning (1) model-based reinforcement learning (1) adaptive regularization (1) off-policy reinforcement learning (1) zero-shot generalization (1) world model (1) dynamics model (1) self-supervised adaptation (1) convolutional encoder (1) dynamics generalization (1) catastrophic self-overfitting (1)

Papers

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels ICML 2022 Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment ICML 2021