This repository is used to house some algorithm implementations in the field of reinforcement learning. Please feel free to refer to them if needed:)
- Value-based (for CartPole-v1)
- Q-learning (tabular)
- DQN
- Policy-based (for CartPole-v1)
- REINFORCE (with baseline)
- A2C (Multi-step TD)
- Continuous Control (for MountainCarContinuous-v0)
- DDPG
- TD3
- SAC
- PPO