Algorithm learns to solve tasks by gradually expanding policy space.
problem Reinforcement learning difficulty progression.
method Decreasingly constrained policy space expansion.
result Superior learning rate in Tetris tasks.
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.
168,742 papers · 148 categories
Trend · papers per month
7 results for “Tetris”
SMiRL learns to minimize surprise in unstable environments, improving agent performance.
problem Learning useful behaviors in unpredictable, unstable environments.
method Alternates between learning a density model and improving policy to seek more predictable stimuli.
result SMiRL agents can play games, control robots, and navigate mazes without task-specific rewards.
Conditional Value at Risk (CVaR) is a prominent risk measure that is being used extensively in various domains. We develop a new formula for the gradient of the CVaR in the form of a conditional expectation. Based on this formula, we propose a novel sampling-based estimator for the CVaR gradient, in the spirit of the l…
User interfaces provide an interactive window between physical and virtual environments. A new concept in the field of human-computer interaction is a soft user interface; a compliant surface that facilitates touch interaction through deformation. Despite the potential of these interfaces, they currently lack a signal …
Balancing the Payment Systemq-fin.GN
Paper introduces balanced payment systems to improve liquidity and risk management.
problem Managing liquidity in payment systems and economy is a persistent challenge.
method Introduces interbank balancing method to private payment systems and others.
result Demonstrates effects of balancing on a small example and constructs a balanced subsystem.
A new geometric perceptron model improves 3D shape classification.
problem Challenges in geometric tasks involving point clouds using machine learning.
method Introduces multilayer geometric perceptron (MLGP) with geometric neurons.
result MLGP outperforms vanilla MLP in 3D shape classification and noise resistance.
We explore the effect of introducing prior information into the intermediate level of neural networks for a learning task on which all the state-of-the-art machine learning algorithms tested failed to learn. We motivate our work from the hypothesis that humans learn such intermediate concepts from other individuals via…