Policy-Gradient-Methods

My implementations of some policy gradient algorithms

• All implementations are written in pytorch
• The algorithms are implemented as classes
• All implementations are encapsulated in a single file
• The algorithms take OpenAI gym envs and Pybullet envs as inputs

Algorithms:

• Vanilla Policy Gradient (VPG)
• Deep Deterministic Policy Gradient (DDPG)
• Twin Delayed DDPG (TD3)
• Soft Actor Critic
• Proximal Policy Optimization

References:

1. Policy Gradient Methods for Reinforcement Learning with Function Approximation
2. Continuous control with deep reinforcement learning
3. Addressing Function Approximation Error in Actor-Critic Methods
4. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
5. Proximal Policy Optimization Algorithms