Sökning: "Sparse rewards environment"

Hittade 5 uppsatser innehållade orden Sparse rewards environment.

1. 1. The effects of multistep learning in the hard-exploration problem

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Jacob Friman; [2022]
   Nyckelord :;

   Sammanfattning : Reinforcement learning is a machine learning field which has received revitalised interest in later years due to many success stories and advancements in deep reinforcement learning. A key part in reinforcement learning is the need for exploration of the environment so the agent can properly learn the best policy. LÄS MER

3. 2. Benchmarking Deep Reinforcement Learning on Continuous Control Tasks : AComparison of Neural Network Architectures and Environment Designs

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Daniel Sahlin; [2022]
   Nyckelord :Deep learning; Reinforcement learning; Reward functions; Neural networks; Furuta pendulum; Djupinlärning; Förstärkningsinlärning; Belöningsfunktioner; Neurala nätverk; Furuta-pendel;

   Sammanfattning : Deep Reinforcement Learning (RL) has received much attention in recent years. This thesis investigates how reward functions, environment termination conditions, Neural Network (NN) architectures, and the type of the deep RL algorithm aect the performance for continuous control tasks. LÄS MER

4. 3. Asynchronous Advantage Actor-Critic and Flappy Bird

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Marcus Wibrink; Markus Fredriksson; [2021]
   Nyckelord :reinforcement learning; A3C; entropy; A3C lambda ; Cart-Pole; Flappy Bird; sparse rewards;

   Sammanfattning : Games provide ideal environments for assessingreinforcement learning algorithms because of their simple dynamicsand their inexpensive testing, compared to real-worldenvironments. Asynchronous Advantage Actor-Critic (A3C), developedby DeepMind, has shown significant improvements inperformance over other state-of-the-art algorithms on Atarigames. LÄS MER

5. 4. An Evaluation of the Unity Machine Learning Agents Toolkit in Dense and Sparse Reward Video Game Environments

   Kandidat-uppsats, Uppsala universitet/Institutionen för speldesign

   Författare :Jari Hanski; Kaan Baris Biçak; [2021]
   Nyckelord :Unity; ML-Agents; Reinforcement learning; Sparse rewards environment; Artificial Intelligence;

   Sammanfattning : In computer games, one use case for artificial intelligence is used to create interesting problems for the player. To do this new techniques such as reinforcement learning allows game developers to create artificial intelligence agents with human-like or superhuman abilities. LÄS MER

7. 5. Impact of observation noise and reward sparseness on Deep Deterministic Policy Gradient when applied to inverted pendulum stabilization

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Adam Björnberg; Haris Poljo; [2019]
   Nyckelord :;

   Sammanfattning : Deep Reinforcement Learning (RL) algorithms have been shown to solve complex problems. Deep Deterministic Policy Gradient (DDPG) is a state-of-the-art deep RL algorithm able to handle environments with continuous action spaces. LÄS MER