On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “dreamer”

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstructioncs.LG

New Dreamer model tackles object vanishing in robot learning.

problem Object vanishing in Dreamer's latent state-space models.

method Decoder-free approach with InfoMax objective and data augmentation.

result Dreaming achieves best scores on 5 difficult robotics tasks.

Dreamer Reinforcement Learning Model-based Latent Imagination InfoMax

2020-07-29abs ↗pdf ↗

DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecastingcs.LG

Enhanced decision-making through Dreamer's anticipatory trajectories and Online Decision Transformer.

problem Efficiently integrating world models with decision transformers.

method Combining Dreamer's trajectory forecasting with Online Decision Transformer's adaptive learning.

result Notable improvements in sample efficiency and reward maximization.

reinforcement learning decision transformers Dreamer trajectory forecasting sample efficiency

2024-10-15abs ↗pdf ↗

Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidancecs.LG

A new algorithm improves model-based reinforcement learning by guiding latent representations.

problem Improving model-based reinforcement learning through additional supervision.

method Proposed a novel asymmetric representation learning objective using latent guidance.

result Significantly improved performance over previous asymmetric approaches.

reinforcement learning model-based asymmetric latent guidance dreamer

2026-07-28abs ↗pdf ↗

Training Agents Inside of Scalable World Modelscs.AI

Dreamer 4 learns Minecraft tasks from videos alone.

problem Accurately predicting object interactions in complex environments.

method Reinforcement learning inside a fast, accurate world model.

result Dreamer 4 outperforms previous models in Minecraft, learning from only offline data.

Dreamer 4 Minecraft Reinforcement Learning World Model Scalable Agent

2025-09-29abs ↗pdf ↗

Mastering Diverse Domains through World Modelscs.AI

DreamerV3 learns diverse tasks with a single configuration.

problem Generalizing reinforcement learning across multiple domains.

method World model and farsighted strategies.

result Outperforms specialized methods across 150 diverse tasks.

reinforcement learning world models generalization diverse tasks open world

2023-01-10abs ↗pdf ↗

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscs.LG

Simple image augmentation boosts deep RL from pixels.

problem Training deep RL models from raw pixel inputs is challenging.

method Applying standard computer vision data augmentation to reinforcement learning.

result Our method significantly improves SAC's performance on DeepMind control suite.

reinforcement learning deep learning image pixels data augmentation value function

2020-04-28abs ↗pdf ↗

Mastering Atari with Discrete World Modelscs.LG

DreamerV2 learns Atari game behaviors from a world model, achieving human-level performance.

problem Learning complex behaviors in Atari games from limited data.

method DreamerV2 uses a world model with discrete representations to predict behaviors in a compact latent space.

result Achieves human-level performance on 55 Atari tasks.

Atari games reinforcement learning world models discrete representations human-level performance

2020-10-05abs ↗pdf ↗

Utilizing Deep Learning Towards Multi-modal Bio-sensing and Vision-based Affective Computingcs.LG

In recent years, the use of bio-sensing signals such as electroencephalogram (EEG), electrocardiogram (ECG), etc. have garnered interest towards applications in affective computing. The parallel trend of deep-learning has led to a huge leap in performance towards solving various vision-based research problems such as o…

2019-05-16abs ↗pdf ↗