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

7 results for “MineRL”

MineRL: A Large-Scale Dataset of Minecraft Demonstrationscs.LG

MineRL dataset tackles reinforcement learning with over 60M annotated state-action pairs.

problem Sample inefficiency in reinforcement learning methods.

method Large-scale, simulator-paired dataset of human demonstrations in Minecraft.

result Demonstrates the scale, diversity, and difficulty of Minecraft tasks.

reinforcement learning MineRL Minecraft human demonstrations state-action pairs

2019-07-29abs ↗pdf ↗

Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learningcs.LG

MineRL Competition reduced reinforcement learning sample needs.

problem Sample inefficiency in reinforcement learning.

method Human demonstrations and imitation learning integrated into reinforcement learning algorithms.

result Top solutions used deep reinforcement learning and imitation learning.

reinforcement learning sample efficiency human demonstrations deep learning imitation learning

2020-03-10abs ↗pdf ↗

Scaling Imitation Learning in Minecraftcs.LG

Researchers improved Minecraft game performance using imitation learning.

problem Achieving state-of-the-art performance in immersive environments like Minecraft.

method Applied imitation learning to Minecraft, optimizing network architecture, loss function, and data augmentation.

result Reported stronger results than previous experiments, reaching second place in a competition.

Imitation Learning Minecraft Sensorimotor Coordination NeurIPS 2019 Data Augmentation

2020-07-06abs ↗pdf ↗

The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priorscs.LG

Competition aims to develop sample-efficient reinforcement learning methods.

problem Limited access to samples in reinforcement learning.

method Develops algorithms leveraging human demonstrations in Minecraft.

result Fosters innovation in sample-efficient reinforcement learning.

reinforcement learning sample efficiency human demonstrations reinforcement learning competition Minecraft

2021-01-26abs ↗pdf ↗

The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priorscs.LG

Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinforcement learning (RL) systems require an exponentially increasing number of samples, their development is restricted to a continually shrin…

2019-04-22abs ↗pdf ↗

Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraftcs.LG

Improved reinforcement learning in Minecraft with human demonstrations.

problem Sample inefficiency in reinforcement learning.

method Training policy networks on human demonstrations first, then fine-tuning with reinforcement learning.

result Best agent achieved a mean score of 48 in Minecraft.

reinforcement learning Minecraft human demonstrations sample efficiency minigame

2020-03-12abs ↗pdf ↗

Towards robust and domain agnostic reinforcement learning competitionscs.LG

New framework promotes reproducible, domain-agnostic reinforcement learning algorithms.

problem Domain-specific, compute-resource-maximizing, and non-reproducible participant solutions in reinforcement learning competitions.

method Submission retraining, domain randomization, desemantization through domain obfuscation, and compute/environment-sample budget limitation.

result Participant submissions are reproducible, non-specific to the competition environment, and sample/resource efficient.

reinforcement learning competitions domain agnostic reproducibility sample efficiency

2021-06-07abs ↗pdf ↗