The GitHub repository for "Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo", AISTATS 2024.

A simple exercise in reinforcement learning

Single-file demo of RELAX/CONSTRAIN control loop with frame shifting and Merkle-like lineage.

Upper Confidence Bound (UCB) multi-armed bandit algorithm for ad click-through rate optimization over 10,000 rounds

OSPO is a novel metaheuristic algorithm which has the potential to solve different kinds of problems with promising performance.

NoisyQ is a noise-based exploration method for DDQN

This project uses Reinforcement Learning to teach an agent to drive by itself and learn from its observations so that it can maximize the reward(180+ lines)

Reinforcement Learning (COMP 579) Project

Active versus Passive exploration

over-parameterization = exploration ?

Uses GloVe embeddings + bandit-style exploration/exploitation with adaptive diversification, UCB-driven cluster search, and stagnation recovery.

the HiDeHo (HInts for Directing the Exploration from History of Operations) framework for Pharo

This repository contains two reinforcement learning projects: "Treasure Hunt in the Frozen Lake," which navigates a modified FrozenLake using dynamic programming, and "Optimizing Movie Recommendations," which employs Multi-Armed Bandits to enhance user satisfaction.

OpenAI, gym environment implementation

Repository Containing Comparison of two methods for dealing with Exploration-Exploitation dilemma for MultiArmed Bandits

A reinforcement learning project where a snake learns to navigate and survive in a dynamic environment through Q-learning.

A systematic parameter study of exploration–exploitation trade-offs in an Active Inference agent under varying precision and sensory noise.

Investigating different exploration strategies and their hyperparameters on a 10-arm bandit testbed inspired by Reinforcement Learning: An Introduction (Sutton & Barto)

Deep Intrinsically Motivated Exploration in Continuous Control