vimmoos@Thor
commited on
Commit
·
a5d959a
1
Parent(s):
f502542
update readme
Browse files
README.md
CHANGED
|
@@ -20,6 +20,9 @@ tags:
|
|
| 20 |
# Upside-Down RL
|
| 21 |
|
| 22 |
This project implements an Upside-Down Reinforcement Learning (UDRL) agent.
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
### Installation
|
| 25 |
|
|
@@ -54,7 +57,6 @@ Available options include:
|
|
| 54 |
* `--batch_size`: Batch size for training (default: `0`, uses entire replay buffer)
|
| 55 |
* Other options related to warm-up, memory size, exploration, testing, saving, etc.
|
| 56 |
|
| 57 |
-
**NOTE** Cartpole, Acrobot, Mountain car and LunarLander envs were tested
|
| 58 |
|
| 59 |
### Result Data
|
| 60 |
|
|
@@ -79,4 +81,4 @@ Please refer to the code and comments for further details on the implementation.
|
|
| 79 |
|
| 80 |
## Troubleshooting
|
| 81 |
|
| 82 |
-
If you encounter any errors during installation or execution, or if you have any questions about the project, feel free to reach out to me at [[email protected]](mailto:[email protected]). I'll be happy to assist you!
|
|
|
|
| 20 |
# Upside-Down RL
|
| 21 |
|
| 22 |
This project implements an Upside-Down Reinforcement Learning (UDRL) agent.
|
| 23 |
+
This is the codebase of the paper: [arXiv](https://arxiv.org/abs/2411.11457)
|
| 24 |
+
The website associated with it is: [demo](https://huggingface.co/spaces/vimmoos/udrl)
|
| 25 |
+
|
| 26 |
|
| 27 |
### Installation
|
| 28 |
|
|
|
|
| 57 |
* `--batch_size`: Batch size for training (default: `0`, uses entire replay buffer)
|
| 58 |
* Other options related to warm-up, memory size, exploration, testing, saving, etc.
|
| 59 |
|
|
|
|
| 60 |
|
| 61 |
### Result Data
|
| 62 |
|
|
|
|
| 81 |
|
| 82 |
## Troubleshooting
|
| 83 |
|
| 84 |
+
If you encounter any errors during installation or execution, or if you have any questions about the project, feel free to reach out to me at [[email protected]](mailto:[email protected]) or open an issue. I'll be happy to assist you!
|