# Swimmer#

This environment is part of the Mujoco environments which contains general information about the environment.

Action Space

`Box(-1.0, 1.0, (2,), float32)`

Observation Space

`Box(-inf, inf, (8,), float64)`

import

`gymnasium.make("Swimmer-v4")`

## 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 be `Box(-Inf, Inf, (10,), float64)` where the first two observations 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 `Box(-Inf, Inf, (8,), float64)` 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

1

angle of the first rotor

-Inf

Inf

motor1_rot

hinge

2

angle of the second rotor

-Inf

Inf

motor2_rot

hinge

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

6

angular velocity of first rotor

-Inf

Inf

motor1_rot

hinge

7

angular velocity of second rotor

-Inf

Inf

motor2_rot

hinge

excluded

position of the tip along the x-axis

-Inf

Inf

slider1

slide

position (m)

excluded

position of the tip along the y-axis

-Inf

Inf

slider2

slide

position (m)

## 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) where `ctrl_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

`xml_file`

str

`"swimmer.xml"`

Path to a MuJoCo model

`forward_reward_weight`

float

`1.0`

Weight for forward_reward term (see section on reward)

`ctrl_cost_weight`

float

`1e-4`

Weight for ctrl_cost term (see section on reward)

`reset_noise_scale`

float

`0.1`

Scale of random perturbations of initial position and velocity (see section on Starting State)

`exclude_current_positions_from_observation`

bool

`True`

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 as `xml_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)