conftrace_

world model

189 papers

Explore in graph

Also known as

WM

Co-occurring keywords

model-based reinforcement learning (415) reinforcement learning (4352) autonomous driving (1142) self-supervised learning (3777) representation learning (6206) large language model (13587) video generation (707) video prediction (140) sample efficiency (472) zero-shot learning (3650)

Papers

Deep Hierarchical Planning from Pixels NIPS 2022
Learning General World Models in a Handful of Reward-Free Deployments NIPS 2022
Learning Symmetric Embeddings for Equivariant World Models ICML 2022
Constrained Contrastive Reinforcement Learning ACML 2022
BYOL-Explore: Exploration by Bootstrapped Prediction NIPS 2022
Learning Robust Dynamics through Variational Sparse Gating NIPS 2022
PLM-based World Models for Text-based Games EMNLP 2022
Continual Predictive Learning From Videos CVPR 2022
Toward Compositional Generalization in Object-Oriented World Modeling ICML 2022
Denoised MDPs: Learning World Models Better Than the World Itself ICML 2022
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations ICML 2022
Masked World Models for Visual Control CORL 2022
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games ACL 2022
Reinforcement Learning with Action-Free Pre-Training from Videos ICML 2022
Pathdreamer: A World Model for Indoor Navigation ICCV 2021
On the Model-Based Stochastic Value Gradient for Continuous Reinforcement Learning L4DC 2021
Learning Behaviors through Physics-driven Latent Imagination CORL 2021
The Active Sensing Testbed AAAI 2021
Structured World Belief for Reinforcement Learning in POMDP ICML 2021
Learning Knowledge Graph-based World Models of Textual Environments NIPS 2021
World Model as a Graph: Learning Latent Landmarks for Planning ICML 2021
Deep Innovation Protection: Confronting the Credit Assignment Problem in Training Heterogeneous Neural Architectures AAAI 2021
Temporal Predictive Coding For Model-Based Planning In Latent Space ICML 2021
Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation AAAI 2021
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment ICML 2021