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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Sokoban”

Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokobancs.LG

Modular RL modules solve complex 3D Sokoban tasks.

problem Solving complex, integrated tasks combining visual, physical, and abstract reasoning.

method Compose RL modules in a sense-plan-act hierarchy, using only model-free methods.

result Modular RL outperforms state-of-the-art monolithic RL on Mujoban.

Reinforcement Learning 3D Sokoban Modular Design Robotics Abstract Reasoning

2020-10-03abs ↗pdf ↗

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecturecs.NE

Novel neural computer learns algorithmic solutions for symbolic tasks.

problem Learning abstract strategies for unfamiliar problems.

method Memory-augmented neural network architecture with Evolution Strategies.

result Strong generalization and abstraction across various tasks.

neural networks symbolic planning algorithmic solutions Evolution Strategies reinforcement learning

2019-10-30abs ↗pdf ↗

Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networkscs.LG

Convolutional networks improve reinforcement learning for navigating all goals.

problem Expensive parallel updates limit reinforcement learning to small tabular cases.

method Use convolutional neural networks to generate Q-values and updates for all goals simultaneously.

result Demonstrated improved accuracy and generalization on various environments.

Reinforcement Learning Convolutional Neural Networks All-Goals Updates Tabular Cases Random Mazes

2018-10-06abs ↗pdf ↗

An investigation of model-free planningcs.LG

Model-free RL agents can learn effective planning without explicit model.

problem Challenging domains with combinatorial complexity.

method Model-free RL with inductive bias in neural networks.

result Model-free RL can exhibit planning characteristics without explicit model.

reinforcement learning model-free planning neural networks Sokoban

2019-01-11abs ↗pdf ↗

Learning to Search with MCTSnetscs.AI

Planning problems are among the most important and well-studied problems in artificial intelligence. They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree. Among these algorithms, Monte-Carlo tree …

2018-02-13abs ↗pdf ↗

Uncertainty-sensitive Learning and Planning with Ensemblescs.LG

A reinforcement learning framework combining value function and tree search planner for strategic and tactical decisions.

problem Strategic and tactical decision-making in discrete environments.

method Combines value function and tree search planner, using uncertainty modeling and risk measurement.

result Improves performance and learning speed on hard exploration environments.

reinforcement learning strategic decisions tactical decisions value function tree search

2019-12-19abs ↗pdf ↗