https://github.com/kanishknavale/ddpg-per-pen
The DDPG algorithm incorporates Actor-Critic Deep Learning Agent for solving continuous action reinforcement learning problems.
https://github.com/kanishknavale/ddpg-per-pen
actor-critic continuous-action-space ddpg ddpg-agent deep-learning deep-reinforcement-learning lunarlandercontinous-v2 openai-gym parameter-noise prioritized-experience-replay python3 pytorch reinforcement-learning
Last synced: 7 months ago
JSON representation
The DDPG algorithm incorporates Actor-Critic Deep Learning Agent for solving continuous action reinforcement learning problems.
- Host: GitHub
- URL: https://github.com/kanishknavale/ddpg-per-pen
- Owner: KanishkNavale
- Created: 2021-03-01T22:16:36.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2022-04-04T17:09:57.000Z (over 3 years ago)
- Last Synced: 2025-04-02T02:03:17.630Z (8 months ago)
- Topics: actor-critic, continuous-action-space, ddpg, ddpg-agent, deep-learning, deep-reinforcement-learning, lunarlandercontinous-v2, openai-gym, parameter-noise, prioritized-experience-replay, python3, pytorch, reinforcement-learning
- Language: Python
- Homepage:
- Size: 20 MB
- Stars: 7
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# DDPG with Parametric Noise Exploration & Prioritized Experience Replay Buffer
This repository implements a DDPG agent with parametric noise for exploration and prioritized experience replay buffer to train the agent faster and better for the openai-gym's "LunarLanderContinuous-v2".
Let's see how fast and better it is!
## Agent Profile
1. DDPG + PNE + PER
2. Vanilla DDPG (I like Vanilla that is why! :>)
## Dependencies
Install dependencies using this,
```bash
pip install -r requirements.txt
```
## TODO
- Add adaptive parametric noise for exploration
## Contact
- Name: Kanishk Navale
- Email: navalekanishk@gmail.com
- Website: