连续控制
Continuous Control是指在游戏等环境中,通过一系列平滑、持续的调整或动作来实现精准控制的能力。其目标是在需要精确度、时机和动作幅度的场景中,优化决策过程和执行效果。Continuous Control在赛车游戏、角色模拟和飞行模拟器等应用中具有重要价值,能够提升系统的响应性和灵活性,增强用户体验和系统性能。
PyBullet Ant
TD3 gSDE
PyBullet HalfCheetah
SAC
PyBullet Hopper
PyBullet Walker2D
Lunar Lander (OpenAI Gym)
MAC
DeepMind Cheetah Run (Images)
DrQ
cartpole.balance_sparse
cartpole.swingup
cheetah.run
DeepMind Cup Catch (Images)
DrQ
DeepMind Walker Walk (Images)
DrQ
finger.turn_hard
walker.stand
walker.walk
2D Walker
Acrobot
Acrobot (limited sensors)
Acrobot (noisy observations)
acrobot.swingup
SMuZero
Acrobot (system identifications)
Ant
Ant + Gathering
Ant + Maze
Ball in cup, catch (DMControl500k)
Ball in cup, catch (DMControl100k)
ball_in_cup.catch
Cart-Pole Balancing
TRPO
Cart-Pole Balancing (limited sensors)
Cart-Pole Balancing (noisy observations)
Cart-Pole Balancing (system identifications)
Cart Pole (OpenAI Gym)
MAC
cartpole.balance
Cartpole, swingup (DMControl500k)
Cartpole, swingup (DMControl100k)
cartpole.swingup_sparse
Cheetah, run (DMControl500k)
Cheetah, run (DMControl100k)
Double Inverted Pendulum
Finger, spin (DMControl500k)
CURL
Finger, spin (DMControl100k)
finger.spin
finger.turn_easy
fish.swim
Full Humanoid
Half-Cheetah
Hopper
hopper.hop
hopper.stand
humanoid.run
Inverted Pendulum
TRPO
Inverted Pendulum (limited sensors)
Inverted Pendulum (system identifications)
Inverted Pendulum (noisy observations)
manipulator.insert_ball
manipulator.insert_peg
Mountain Car
Mountain Car (limited sensors)
Mountain Car (noisy observations)
Mountain Car (system identifications)
pendulum.swingup
quadruped.run
quadruped.walk
Reacher, easy (DMControl500k)
Reacher, easy (DMControl100k)
reacher.easy
reacher.hard
Simple Humanoid
Swimmer
Swimmer + Gathering
Swimmer + Maze
walker.run
Walker, walk (DMControl500k)
CURL
Walker, walk (DMControl100k)