I recently just completed and open sourced my Pytorch implementation of a Deep Q-Network(DQN) to play Atari Pong. The implementation follows from the paper - Playing Atari with Deep Reinforcement Learning (DQN_neurips implementation) and Human-level control through deep reinforcement learning (DQN_nature implementation).
You can train your agent from scarch or load a trained policy from a checkpoint file and see videos as your agent is training.
Hey everyone I just learned that music is just not for listening and dancing to all the time it much more then that it expressed your feelings and how you are upset or in love you put it in a song that talk about your feelings to other people it helps you understand what going on or why are you upset and in love
2 comments
[ 3.3 ms ] story [ 17.9 ms ] threadI recently just completed and open sourced my Pytorch implementation of a Deep Q-Network(DQN) to play Atari Pong. The implementation follows from the paper - Playing Atari with Deep Reinforcement Learning (DQN_neurips implementation) and Human-level control through deep reinforcement learning (DQN_nature implementation).
You can train your agent from scarch or load a trained policy from a checkpoint file and see videos as your agent is training.
Here is a video (https://www.youtube.com/watch?v=DcyMFIKsVNI) of one the agent's games once it had learned a policy.
Any comments or points are welcome. :)