Reinforcement learning algorithms for a visual input task
1 Deep Deterministic Policy Gradients (DDPG)
- DDPG with vector input: ddpg_vec.ipynb
- DDPG with visual input: ddpg_vis.ipynb
2 Deep Q-Network (DQN)
- DQN with vector input: dqn_vec.ipynb
- DQN with visual input: dqn_vis.ipynb
- DQN + LSTM with visual input: dqn_lstm_vis.ipynb
Results can be found in report.pdf