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.

169,042 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “pseudo-rewards”

Perturbed-History Exploration in Stochastic Multi-Armed Banditscs.LG

PHE adds pseudo-rewards to history to minimize regret in stochastic bandits.

problem Minimizing cumulative regret in stochastic multi-armed bandits.

method PHE algorithm that adds

O(t)

i.i.d. pseudo-rewards to history and pulls the best arm based on the perturbed history.

result Near-optimal regret bounds derived for PHE.

stochastic multi-armed bandits cumulative regret pseudo-rewards optimism Bernoulli rewards

2019-02-26abs ↗pdf ↗

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Banditscs.LG

We propose a bandit algorithm that explores by randomizing its history of rewards. Specifically, it pulls the arm with the highest mean reward in a non-parametric bootstrap sample of its history with pseudo rewards. We design the pseudo rewards such that the bootstrap mean is optimistic with a sufficiently high probabi…

2018-11-13abs ↗pdf ↗

Successor Options: An Option Discovery Framework for Reinforcement Learningcs.LG

Successor Options discovers reusable skills using landmark states.

problem Discovering reusable skills in reinforcement learning.

method Leverages Successor Representations to build a state space model and learns intra-option policies using a novel pseudo-reward.

result Demonstrates the approach's efficacy on grid-worlds and high-dimensional robotic control environments.

reinforcement learning option discovery successor representations landmark states pseudo-reward

2019-05-14abs ↗pdf ↗

Perturbed-History Exploration in Stochastic Linear Banditscs.LG

New algorithm minimizes regret in stochastic linear bandits with perturbed history.

problem Minimizing cumulative regret in stochastic linear bandits.

method Perturbed-history exploration in a linear bandit (LinPHE) algorithm.

result Achieves a

O(d \sqrt{n})

gap-free bound on cumulative regret.

stochastic linear bandits cumulative regret perturbed history online algorithms linear model

2019-03-21abs ↗pdf ↗

Paper shows RL's policy gradient methods can be viewed as supervised learning problems.

problem Connecting RL and SL approaches.

method Proves PGM as supervised learning problem, replaces true labels with discounted rewards.

result PGM can be seen as supervised learning, emphasizing similarities.

policy gradient methods reinforcement learning supervised learning gradient descent rewards

2019-04-12abs ↗pdf ↗

Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPscs.LG

New algorithm for RL with horizon-free reward-free exploration for linear MDPs.

problem Reward-free reinforcement learning with long planning horizons.

method Uncertainty-weighted value-targeted regression with exploration-driven pseudo-reward and moment estimator.

result Horizon-free sample complexity of

O(d^2\varepsilon^{-2})

for finding an

\varepsilon

-optimal policy.

reinforcement learning reward-free horizon-free linear MDPs value-targeted regression

2023-03-17abs ↗pdf ↗