Carla follow lane DDPG vs PPO
Follow lane carla ppo Vs dppg
Logbook
2024
Carla follow lane (2024)
migration to carla and follow lane problem
2023
Gazebo F1 Follow line algorithms comparison (months 35, 36 and 37)
all algorithms comparison
Gazebo F1 Follow line ddpg (months 33 and 34)
Qlearning and DQN f1 follow line gazebo comparison
Gazebo F1 Follow line dqn & qlearning comparison (months 29, 30, 31, 32)
Qlearning and DQN f1 follow line gazebo comparison
Cartpole problem solution final tuning and conclusions (months 27 and 28)
Qlearning and DQN cartpole problems included
2022
Cartpole problem solution comparisson with different algorithms and articles analysis (month 24, 25 and 26)
Qlearning and DQN cartpole problems included
Included random initial positions and random perturbations to cartpole problem (month 23)
Qlearning and DQN cartpole problems included
Cartpole problem extended to be solved with DQN (month 21 and 22)
DQN cartpole problem included
OpenAIGym simulator included in RL-Studio to include canonical problems with Cartpole as the guinea pig one (month 20)
Qlearning cartpole problem included
RL-Studio refinement and article writing (Month 18 and 19)
RL-Studio was bornt! We got to write an article
JdeRobot team allignment & inference rlstudio module created (month 17)
final allignment within the team to progress in same direction and creation of rl-studio inferencer module
JdeRobot team RLStudio 1.1 allignment (months 15 and 16)
migration of problems to new version, documentation and some refactors applied
Projects polishing pre-integration with RL-Studio 1.1.0 (month 14)
Projects fixes, algorithms fine tuning and algorighms course
2021
Final implementation of mountain_car basic scenario (Month 13 - Second half)
Implemented first prototype for mountain car in RL-Studio
Still migrating mountain car to RL-Studio and year 1 phd formalization (Month 13 - First half)
Keep working on mountain car (adapted to RL-Studio version) and formalize the phd burocracy
Migrating to new RLStudio and migrating mountain car to RLStudio 0.1.0 (Month 12)
Run Nacho TFM in new RLStudio and adapt mountain car made problem to work on it
Learning about RLStudio with basic robot mesh problem (months 10 and 11)
Run Nacho TFM in RLStudio and adapt robot_mesh made problem to work on it
Introduction to gazebo and rl-studio (months 8 and 9)
Learning about gazebo and rl-studio to later develop in this environment
Study of first section of sutton book (month 7)
Reinforcement of RL basics to be able to perform good practices when developing
Projects standarization (month 6)
Standarizing the project folders and the exercises code structure
QLearning (month 5 · Weeks 3 and 4)
Creating our own environment to freely configure our own problem
QLearning (month 5 · Weeks 1 and 2)
Solving a more complex problem using qlearning
Projects polishing pre-integration with RL-Studio 1.1.0 (month 14)
Projects fixes, algorithms fine tuning and algorighms course
QLearning and Sarsa (month 4)
Start playing with reinforcement learning
2020
Digging in (month 3)
Start playing with reinforcement learning
Introduction (months 1 and 2)
Landing on vision recognition basics