Swimmer#
![../../../_images/swimmer.gif](../../../_images/swimmer.gif)
This environment is part of the Mujoco environments.Please read that page first for general information.
Action Space |
Box(-1.0, 1.0, (2,), float32) |
Observation Shape |
(8,) |
Observation High |
inf |
Observation Low |
-inf |
Import |
|
Description#
This environment corresponds to the Swimmer environment described in Rémi Coulom’s PhD thesis “Reinforcement Learning Using Neural Networks, with Applications to Motor Control”. The environment aims to increase the number of independent state and control variables as compared to the classic control environments. The swimmers consist of three or more segments (’links’) and one less articulation joints (’rotors’) - one rotor joint connecting exactly two links to form a linear chain. The swimmer is suspended in a two dimensional pool and always starts in the same position (subject to some deviation drawn from an uniform distribution), and the goal is to move as fast as possible towards the right by applying torque on the rotors and using the fluids friction.
Notes#
The problem parameters are: Problem parameters:
n: number of body parts
mi: mass of part i (i ∈ {1…n})
li: length of part i (i ∈ {1…n})
k: viscous-friction coefficient
While the default environment has n = 3, li = 0.1, and k = 0.1. It is possible to pass a custom MuJoCo XML file during construction to increase the number of links, or to tweak any of the parameters.
Action Space#
The action space is a Box(-1, 1, (2,), float32)
. An action represents the torques applied between links
Num |
Action |
Control Min |
Control Max |
Name (in corresponding XML file) |
Joint |
Unit |
---|---|---|---|---|---|---|
0 |
Torque applied on the first rotor |
-1 |
1 |
motor1_rot |
hinge |
torque (N m) |
1 |
Torque applied on the second rotor |
-1 |
1 |
motor2_rot |
hinge |
torque (N m) |
Observation Space#
By default, observations consists of:
θi: angle of part i with respect to the x axis
θi’: its derivative with respect to time (angular velocity)
In the default case, observations do not include the x- and y-coordinates of the front tip. These may
be included by passing exclude_current_positions_from_observation=False
during construction.
Then, the observation space will have 10 dimensions where the first two dimensions
represent the x- and y-coordinates of the front tip.
Regardless of whether exclude_current_positions_from_observation
was set to true or false, the x- and y-coordinates
will be returned in info
with keys "x_position"
and "y_position"
, respectively.
By default, the observation is a ndarray
with shape (8,)
where the elements correspond to the following:
Num |
Observation |
Min |
Max |
Name (in corresponding XML file) |
Joint |
Unit |
---|---|---|---|---|---|---|
0 |
angle of the front tip |
-Inf |
Inf |
free_body_rot |
hinge |
angle (rad) |
1 |
angle of the first rotor |
-Inf |
Inf |
motor1_rot |
hinge |
angle (rad) |
2 |
angle of the second rotor |
-Inf |
Inf |
motor2_rot |
hinge |
angle (rad) |
3 |
velocity of the tip along the x-axis |
-Inf |
Inf |
slider1 |
slide |
velocity (m/s) |
4 |
velocity of the tip along the y-axis |
-Inf |
Inf |
slider2 |
slide |
velocity (m/s) |
5 |
angular velocity of front tip |
-Inf |
Inf |
free_body_rot |
hinge |
angular velocity (rad/s) |
6 |
angular velocity of first rotor |
-Inf |
Inf |
motor1_rot |
hinge |
angular velocity (rad/s) |
7 |
angular velocity of second rotor |
-Inf |
Inf |
motor2_rot |
hinge |
angular velocity (rad/s) |
Rewards#
The reward consists of two parts:
forward_reward: A reward of moving forward which is measured as
forward_reward_weight
* (x-coordinate before action - x-coordinate after action)/dt. dt is the time between actions and is dependent on the frame_skip parameter (default is 4), where the frametime is 0.01 - making the default dt = 4 * 0.01 = 0.04. This reward would be positive if the swimmer swims right as desired.ctrl_cost: A cost for penalising the swimmer if it takes actions that are too large. It is measured as
ctrl_cost_weight
* sum(action2) wherectrl_cost_weight
is a parameter set for the control and has a default value of 1e-4
The total reward returned is reward = forward_reward - ctrl_cost and info
will also contain the individual reward terms
Starting State#
All observations start in state (0,0,0,0,0,0,0,0) with a Uniform noise in the range of [-reset_noise_scale
, reset_noise_scale
] is added to the initial state for stochasticity.
Episode End#
The episode truncates when the episode length is greater than 1000.
Arguments#
No additional arguments are currently supported in v2 and lower.
import gymnasium as gym
gym.make('Swimmer-v4')
v3 and v4 take gymnasium.make
kwargs such as xml_file
, ctrl_cost_weight
, reset_noise_scale
, etc.
import gymnasium as gym
env = gym.make('Swimmer-v4', ctrl_cost_weight=0.1, ....)
Parameter |
Type |
Default |
Description |
---|---|---|---|
|
str |
|
Path to a MuJoCo model |
|
float |
|
Weight for forward_reward term (see section on reward) |
|
float |
|
Weight for ctrl_cost term (see section on reward) |
|
float |
|
Scale of random perturbations of initial position and velocity (see section on Starting State) |
|
bool |
|
Whether or not to omit the x- and y-coordinates from observations. Excluding the position can serve as an inductive bias to induce position-agnostic behavior in policies |
Version History#
v4: All MuJoCo environments now use the MuJoCo bindings in mujoco >= 2.1.3
v3: Support for
gymnasium.make
kwargs such asxml_file
,ctrl_cost_weight
,reset_noise_scale
, etc. rgb rendering comes from tracking camera (so agent does not run away from screen)v2: All continuous control environments now use mujoco-py >= 1.50
v1: max_time_steps raised to 1000 for robot based tasks. Added reward_threshold to environments.
v0: Initial versions release (1.0.0)