Essays about: "PPO"

Showing result 1 - 5 of 10 essays containing the word PPO.

  1. 1. Animation of humanoid characters using reinforcement learning

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

    Author : Erik Lindström; [2019]
    Keywords : Reinforcement Learning; Animation; Procedural Animation; Simulated Swimming;

    Abstract : Procedural animations are still in its infancy, and one of the techniques to create such is using Reinforcement Learning. In this project, swimming animations are created using UnityML version 0.6 with their Reinforcement Learning training agents, using the policy PPO, created by OpenAI. READ MORE

  2. 2. Using Reinforcement Learning for Games with Nondeterministic State Transitions

    University essay from Linköpings universitet/Statistik och maskininlärning

    Author : Max Fischer; [2019]
    Keywords : reinforcement learning; proximal policy optimization; PPO; machine learning; artificial intelligence; deep learning; neural network; candy crush; mobile game;

    Abstract : Given the recent advances within a subfield of machine learning called reinforcement learning, several papers have shown that it is possible to create self-learning digital agents, agents that take actions and pursue strategies in complex environments without any prior knowledge. This thesis investigates the performance of the state-of-the-art reinforcement learning algorithm proximal policy optimization, when trained on a task with nondeterministic state transitions. READ MORE

  3. 3. Integrating Reinforcement Learning into Behavior Trees by Hierarchical Composition

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

    Author : Mart Kartasev; [2019]
    Keywords : ;

    Abstract : This thesis investigates ways to extend the use of Reinforcement Learning (RL) to Behavior Trees (BTs). BTs are used in the field of Artificial Intelligence (AI) in order to create modular and reactive planning agents. READ MORE

  4. 4. Intelligent Formation Control using Deep Reinforcement Learning

    University essay from Linköpings universitet/Artificiell intelligens och integrerade datorsystem

    Author : Rasmus Johns Johns; [2018]
    Keywords : ;

    Abstract : In this thesis, deep reinforcement learning is applied to the problem of formation control to enhance performance. The current state-of-the-art formation control algorithms are often not adaptive and require a high degree of expertise to tune. READ MORE

  5. 5. Simulating market maker behaviour using Deep Reinforcement Learning to understand market microstructure

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

    Author : Elwin Marcus; [2018]
    Keywords : Deep Reinforcement Learning; Machine Learning; Market Microstructure; Market Maker; Financial Agent; Agent Based Modelling; Financial Artificial Markets; Complex Systems; Algorithmic Trading; Tensorforce; keras-RL; PPO; DQN; Dealer Market; Limit Order book;

    Abstract : Market microstructure studies the process of exchanging assets underexplicit trading rules. With algorithmic trading and high-frequencytrading, modern financial markets have seen profound changes in marketmicrostructure in the last 5 to 10 years. READ MORE