Essays about: "Performance reward challenges"

Showing result 1 - 5 of 9 essays containing the words Performance reward challenges.

1. 1. Decreasing Training Time of Reinforcement Learning Agents for Remote Tilt Optimization using a Surrogate Neural Network Approximator

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Jiaming Huang; [2023]
   Keywords : ;

   Abstract : One possible application of reinforcement learning in the telecommunication field is antenna tilt optimization. However, one of key challenges we face is that the use of handcrafted simulators as environments to provide information for agents is often time-consuming regarding training reinforcement learning agents. READ MORE

3. 2. Interaction Aware Decision Making for Automated Vehicles Based on Reinforcement Learning

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Ning Wang; [2022]
   Keywords : Reinforcement Learning; Automated Vehicles; Decision-making; Rollout; Driver Behaviour Modeling; Trajectory Prediction; Förstärkningsinlärning; automatiserade fordon; beslutsfattande; utrullning; modellering av förarbeteende; banförutsägelse;

   Abstract : Decision-making is one of the key challenges blocking full autonomy of automated vehicles. In highway scenarios, automated vehicles are expected to be aware of their surroundings and make decisions by interacting with other road participants to drive safely and efficiently. READ MORE

4. 3. Belief-aided Robust Control for Remote Electrical Tilt Optimization

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Jack Jönsson; [2021]
   Keywords : Mobile Network Optimization; Remote Electrical Tilt; Robust Control; Reinforcement Learning; Partially Observable Markov Decision Process; Belief State Estimation; Bayesian Neural Network; Optimering av Mobilnätverk; Fjärrstyrning av Elektrisk Lutning; Robust Reglering; Delvis Observerbar Markovprocess; Tillståndsestimering; Bayesiskt Neuralt Nätverk;

   Abstract : Remote Electrical Tilt (RET) is a method for configuring antenna downtilt in base stations to optimize mobile network performance. Reinforcement Learning (RL) is an approach to automating the process by letting an agent learn an optimal control strategy and adapt to the dynamic environment. READ MORE

5. 4. Domain independent enhancements to Monte Carlo tree search for eurogames

   University essay from Mittuniversitetet/Institutionen för data- och systemvetenskap

   Author : Peter Bergh; [2020]
   Keywords : Monte Carlo tree search · Domain independence · Stochasticity · Eurogames · Carcassonne;

   Abstract : The Monte Carlo tree search-algorithm (MCTS) has been proven successful when applied to combinatorial games, a term applied to sequential games with perfect information. As the focus for MCTS has tended to lean towards combinatorial games, general MCTS-strategies for other types of board games are hard to find. READ MORE

6. 5. Improving Generalization in Reinforcement Learningusing Skill-based Rewards

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Francesco Vito Lorenzo; [2020]
   Keywords : ;

   Abstract : Reinforcement Learning is a promising approach to develop intelligent agents that can help game developers in testing new content. However, applying it to a game with stochastic transitions like Candy Crush Friends Saga (CCFS) presents some challenges. READ MORE