https://github.com/pjarbas/deep-rl
Solving gym environments using RLlib: Industry-Grade Reinforcement Learning
https://github.com/pjarbas/deep-rl
deep-learning deep-reinforcement-learning pytorch rllib tensorboard tensorflow
Last synced: 2 months ago
JSON representation
Solving gym environments using RLlib: Industry-Grade Reinforcement Learning
- Host: GitHub
- URL: https://github.com/pjarbas/deep-rl
- Owner: PJarbas
- License: mit
- Created: 2022-10-11T23:08:02.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-10-12T02:29:17.000Z (over 3 years ago)
- Last Synced: 2025-10-06T11:40:41.502Z (9 months ago)
- Topics: deep-learning, deep-reinforcement-learning, pytorch, rllib, tensorboard, tensorflow
- Language: Python
- Homepage:
- Size: 344 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# deep-rl
This project aims to solving gym environments using RLlib: Industry-Grade Reinforcement Learning
### Get started
Ensure that your **python** version is >= 3.9
Train the Agent using the following command:
```bash
$ python train_rl_agent.py
```
### Do inference after training
run the test_rl_agent script using the following command:
```bash
$ python test_rl_agent.py
```
### Tensorboard
```bash
$ tensorboard --logdir=CartPole-v0_results
```
### Results
Best Trial name |iter |total time (s) |reward | episode_reward_max | episode_reward_min |
:------------------------------:|:-----:|:-------------:|:------:|:-------------------:|:------------------:|
PPO_CartPole-v0_e6e3e_00000 | 28 | 145.908 | 197.08 | 200 | 127 |
PPO_LunarLander-v2_db73e_00000 | 148 | 943.732 | 195.263| 301.256 | -153.757 |
Emvironment | Tensorboard
:------------------------------------:|:---------------------------------:
 | 
 | 