MartinThoma / banana-gym
A simple stochastic OpenAI environment for training RL agents
☆89Updated last year
Related projects: ⓘ
- A reinforcement learning framework☆154Updated 5 years ago
- Reinforcement Learning in Keras on VizDoom☆146Updated 6 years ago
- My implementation of the Proximal Policy Optisation algorithm using Keras as a backend☆88Updated 4 years ago
- A PyTorch implementation of Rainbow DQN agent☆164Updated 6 years ago
- Actor-critic with experience replay☆251Updated last year
- C51-DDQN in Keras☆125Updated 6 years ago
- Deep recurrent Q Learning using Tensorflow, openai/gym and openai/retro☆173Updated last year
- implement of prioritized experience replay