Skip to content
/ RL_Dribble Public

Acquisition of robot dribbling motion using reinforcement learning.

1 star 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

matsumotokoki/RL_Dribble

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

57 Commits
png
png
 
 
xml
xml
 
 
.gitignore
.gitignore
 
 
2d_DQN_Dribble.py
2d_DQN_Dribble.py
 
 
DQN_Dribble.py
DQN_Dribble.py
 
 
DQN_Dribble_velocity.py
DQN_Dribble_velocity.py
 
 
DQN_obstacle_avoidance_dribble.py
DQN_obstacle_avoidance_dribble.py
 
 
DQN_obstacle_avoidance_dribble2.py
DQN_obstacle_avoidance_dribble2.py
 
 
DQN_random_obstacles_avoidance_dribble.py
DQN_random_obstacles_avoidance_dribble.py
 
 
README.md
README.md
 
 
all_replay.py
all_replay.py
 
 
debug_sim.py
debug_sim.py
 
 
dribble_env.py
dribble_env.py
 
 
dribble_env_2d.py
dribble_env_2d.py
 
 
dribble_env_velocity.py
dribble_env_velocity.py
 
 
modeling.md
modeling.md
 
 
mymjviewer.py
mymjviewer.py
 
 
obstacle_avoidance_dribble_env.py
obstacle_avoidance_dribble_env.py
 
 
obstacle_avoidance_dribble_env2.py
obstacle_avoidance_dribble_env2.py
 
 
random_obstacles_avoidance_dribble_env.py
random_obstacles_avoidance_dribble_env.py
 
 
replay_data.py
replay_data.py
 
 
xml_reference.md
xml_reference.md
 
 

Repository files navigation

RL_Dribble

10/06

MEMO

  • git管理開始
  • デバック用にマウス操作できるようにする
  • 摩擦がうまく機能していない問題を直す
  • 座標系を活用したい

10/19

MEMO

  • DQNを回せるようになった
    • 評価関数を考える必要あり
    • 入力は4つでいいのか検討 →障害物の数に合わせて変更、速度成分を追加した
  • PID制御のコードもこれから書きたい

11/16

11/28

12/2

12/19

About

Acquisition of robot dribbling motion using reinforcement learning.

Resources

Readme
Activity

Stars

1 star

Watchers

2 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages