# BipedalWalkerHardcore-SAC1

**Repository Path**: ma752753127/bipedal-walker-hardcore-sac1

## Basic Information

- **Project Name**: BipedalWalkerHardcore-SAC1
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-01-11
- **Last Updated**: 2025-01-11

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# SAC BipedalWalkerHardcore

> A sample code used to solve BipedalWalker-v3 & BipedalWalkerHardcore-v3

## Requirement

* [python 3.7](https://www.python.org) 
* [pytorch 1.0.1](https://pytorch.org/) [ Warning ! ]
* (I ever used v1.7, then I waste a month to deal with it using the same code but without any network changes, please be careful!)
* [gym 0.13.1](https://github.com/openai/gym)


## Hyperparameters

Agent uses the following hyperparameters:

```
gamma=0.99
batch_size=256
lr=5e-4
hidden_size=400
tau=0.005
alpha=0.2
reward_scale = 5 // reward *= reward_scale
capacity=2000000
```

## [Techical Report](data/BipedalWalkerTest.md)

https://github.com/CoderAT13/BipedalWalkerHardcore-SAC/blob/main/data/BipedalWalkerTest.md

## How to use my code?

1. Train from blank network

```dotnetcli
$ python main.py --train=1
```

2. Train from exist network

```dotnetcli
$ python main.py --train=1 --load=1
```

3. Play with the network

```dotnetcli
$ python main.py --load=1 --render=1
```

## MyResult

BiliBili: [https://www.bilibili.com/video/BV1DK4y1j7Nz/](https://www.bilibili.com/video/BV1DK4y1j7Nz/)

### Bipedalwalker

![](imgs/normal.png)

### BipedalwalkerHardcore

![](imgs/hardcore.png)

## Credit

Pranjal Tandon (https://github.com/pranz24).