Popular repositories Loading

1. Tennis-MADDPG-PER Tennis-MADDPG-PER Public

   Training multiple agents to play collaboratively using deep reinforcement learning with the MADDPG algorithm and Prioritized Experience Replay.

   Jupyter Notebook 5 1

2. DRL-Soccer-PPO DRL-Soccer-PPO Public

   Training a two player soccer team using Advantage Actor Critic (A2C) with Proximal Policy Optimization (PPO) to beat a random team.

   Jupyter Notebook 4 2

3. DRL-Tennis DRL-Tennis Public

   Training multiple agents to play collaboratively using deep reinforcement learning with the MADDPG algorithm.

   HTML 2

4. DRL-Bananas DRL-Bananas Public

   Training an agent using deep reinforcement learning with the DQN algorithm.

   Jupyter Notebook

5. DRL-Reacher DRL-Reacher Public

   Deep Reinforcement Learning - DDPG Algorithm - Training a continuous control agent in a multi-thread environment.

   Jupyter Notebook 2

6. DeepRL DeepRL Public

   Forked from ShangtongZhang/DeepRL

   Modularized Implementation of Deep RL Algorithms in PyTorch

   Python