DeepReinforcementLearning

Contains codes and reports of running Deep RL techniques on standard simulated environments like openAI Gym, Mujoco etc. The repository will be updated from time to time.

Many of the initial algorithms are solved assignments from UC Berkley, CS 294 deep reinforcement learning fall 2017 Course.

1. Homework 1 : Imitation Learning
2. Homework 2 : Policy Gradients
3. Homework 3 : DQN
4. Homework 4 : Model Based RL

Table of Contents

1. Imitation Learning - DAGGER
2. Policy Gradient - Actor Critic Networks
3. Deep Q Learning and Double Deep Q Learning
4. Model Based RL with Model Predictive Controller(MPC)
5. Deep Deterministic Policy Gradients

Which RL algorithm to use ?

Coming Soon

• Transfer and Life Long Learning - an RL Perspective
• Gradient Free Deep RL

License

• MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT)