dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Updated README.md

Browse Source
This commit is contained in:
ottofabian 2020-12-07 11:25:58 +01:00
parent b4096ad8a2
commit 768ae14655
1 changed files with 14 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -1,7 +1,8 @@
## ALR Custom Environments ## ALR Custom Environments
This repository collects custom RL envs not included in Suits like OpenAI gym, rllab, etc. This repository collects custom RL envs not included in Suits like OpenAI gym, rllab, etc.
Creating a custom (Mujoco) gym environement can be done according to this guide: https://github.com/openai/gym/blob/master/docs/creating-environments.md Creating a custom (Mujoco) gym environement can be done according to [this guide](https://github.com/openai/gym/blob/master/docs/creating-environments.md).
For stochastic search problems with gym interace use the Rosenbrock reference implementation.
## Environments ## Environments
Currently we have the following environements: Currently we have the following environements:
@ -10,8 +11,13 @@ Currently we have the following environements:
|Name| Description| |Name| Description|
|---|---| |---|---|
|`ALRReacher-v0`|modification (5 links) of Mujoco Gym's Reacher (2 links)| |`ALRReacher-v0`|Modified (5 links) Mujoco gym's `Reacher-v2` (2 links)|
|`ALRReacherSparse-v0`|Same as `ALRReacher-v0`, but the distance penalty is only provided in the last time step.| |`ALRReacherSparse-v0`|Same as `ALRReacher-v0`, but the distance penalty is only provided in the last time step.|
|`ALRReacherSparseBalanced-v0`|Same as `ALRReacherSparse-v0`, but the the end effector has to stay upright.|
|`ALRReacherShort-v0`|Same as `ALRReacher-v0`, but the episode length is reduced to 50.|
|`ALRReacherShortSparse-v0`|Combination of `ALRReacherSparse-v0` and `ALRReacherShort-v0`.|
|`ALRReacher7-v0`|Modified (7 links) Mujoco gym's `Reacher-v2` (2 links)|
|`ALRReacher7Sparse-v0`|Same as `ALRReacher7-v0`, but the distance penalty is only provided in the last time step.|
### Classic Control ### Classic Control
@ -19,6 +25,12 @@ Currently we have the following environements:
|---|---| |---|---|
|`SimpleReacher-v0`| Simple Reaching Task without any physics simulation. Returns no reward until 150 time steps. This allows the agent to explore the space, but requires precise actions towards the end of the trajectory.| |`SimpleReacher-v0`| Simple Reaching Task without any physics simulation. Returns no reward until 150 time steps. This allows the agent to explore the space, but requires precise actions towards the end of the trajectory.|
### Stochastic Search
|Name| Description|
|---|---|
|`Rosenbrock{dim}-v0`| Gym interface for Rosenbrock function. `{dim}` is one of 5, 10, 25, 50 or 100. |
## INSTALL ## INSTALL
1. Clone the repository 1. Clone the repository
```bash ```bash