zjowowen commited on
Commit
b64de5f
·
1 Parent(s): 60d49bd

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +7 -5
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  type: CartPole-v0
22
  metrics:
23
  - type: mean_reward
24
- value: 194.3 +/- 7.42
25
  name: mean_reward
26
  ---
27
 
@@ -29,11 +29,10 @@ model-index:
29
 
30
  ## Model Description
31
  <!-- Provide a longer summary of what this model is. -->
32
- This is a simple **MuZero** implementation to OpenAI/Gym/Box2d **CartPole-v0** by using [DI-engine](https://github.com/opendilab/di-engine) and [LightZero](https://github.com/opendilab/LightZero).
33
 
34
- **DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
35
 
36
- **LightZero** is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL).
37
 
38
  ## Model Usage
39
  ### Install the Dependencies
@@ -45,7 +44,10 @@ This is a simple **MuZero** implementation to OpenAI/Gym/Box2d **CartPole-v0** b
45
  git clone https://github.com/opendilab/huggingface_ding.git
46
  pip3 install -e ./huggingface_ding/
47
  # install environment dependencies if needed
48
- pip3 install DI-engine[common_env,video] LightZero
 
 
 
49
  ```
50
  </details>
51
 
 
21
  type: CartPole-v0
22
  metrics:
23
  - type: mean_reward
24
+ value: 198.6 +/- 4.2
25
  name: mean_reward
26
  ---
27
 
 
29
 
30
  ## Model Description
31
  <!-- Provide a longer summary of what this model is. -->
 
32
 
33
+ This implementation applies **MuZero** to the OpenAI/Gym/Box2d **CartPole-v0** environment using [LightZero](https://github.com/opendilab/LightZero) and [DI-engine](https://github.com/opendilab/di-engine).
34
 
35
+ **LightZero** is an efficient, easy-to-understand open-source toolkit that merges Monte Carlo Tree Search (MCTS) with Deep Reinforcement Learning (RL), simplifying their integration for developers and researchers.
36
 
37
  ## Model Usage
38
  ### Install the Dependencies
 
44
  git clone https://github.com/opendilab/huggingface_ding.git
45
  pip3 install -e ./huggingface_ding/
46
  # install environment dependencies if needed
47
+
48
+ pip3 install DI-engine[common_env,video]
49
+ pip3 install LightZero
50
+
51
  ```
52
  </details>
53