paper-with-me

홈 › Papers

Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning

2023-06-05 · Sam Lobel, Akhil Bagaria, George Konidaris

We propose a new method for count-based exploration in high-dimensional state spaces. Unlike previous work which relies on density models, we show that counts can be derived by averaging samples from the Rademacher distribution (or coin flips). This insight is used to set up a simple supervised learning objective which, when optimized, yields a state's visitation count. We show that our method is significantly more effective at deducing ground-truth visitation counts than previous work; when used as an exploration bonus for a model-free reinforcement learning algorithm, it outperforms existing approaches on most of 9 challenging exploration tasks, including the Atari game Montezuma's Revenge.

📄 PDF Abstract BibTeX arXiv:2306.03186

Code (1)

samlobel/cfn 공식 구현 tf

Tasks

Montezuma's Revengereinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Exploration with Limited Memory: Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits

2020-04-09 · Sepehr Assadi, Chen Wang

Consider the following abstract coin tossing problem: Given a set of $n$ coins with unknown biases, find the most biased coin using a minimal number of coin tosses. This is a common abstraction of various exploration pro…

Multi-Armed Bandits

Application of the Kelly Criterion to Prediction Markets

2024-12-18 · Bernhard K Meister

Betting markets are gaining in popularity. Mean beliefs generally differ from prices in prediction markets. Logarithmic utility is employed to study the risk and return adjustments to prices. Some consequences are descri…

Prediction

Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards

2025-10-18 · Xuan Zhang, Ruixiao Li, Zhijian Zhou, Long Li 외 arxiv

Reinforcement Learning (RL) has become a compelling way to strengthen the multi step reasoning ability of Large Language Models (LLMs). However, prevalent RL paradigms still lean on sparse outcome-based rewards and limit…

Reinforcement Learning

Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding

2019-06-11 · Fabrizio Carpi, Christian Häger, Marco Martalò, Riccardo Raheli 외

In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step,…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

The Power of Adaptivity in Identifying Statistical Alternatives

2016-12-01 · NeurIPS 2016 12 · Kevin G. Jamieson, Daniel Haas, Benjamin Recht

This paper studies the trade-off between two different kinds of pure exploration: breadth versus depth. We focus on the most biased coin problem, asking how many total coin flips are required to identify a ``heavy'' coin…

Anomaly Detection