nitish-kalan/cartpole-v1-actor-critic-keras

Solving CartPole-v1 environment in Keras with Actor Critic algorithm an Deep Reinforcement Learning algorithm

CartPole-v1 Actor Critic in Keras

CartPole-v1 is an environment presented by OpenAI Gym. In this repository we have implemented Actor Critic algorithm [1] in Keras for building an agent to solve this CartPole-v1 enviroment.

Commands to run

• To train the model

  python train_model.py
  

• To test the model

  python test_model.py 'path_of_saved_model_weights' (without quotes)
  

• To test agent with our trained weights

  python test_model.py saved_model/475.0.h5
  

Results

• Output of agent taking random actions

  

• Output of our agent at Episode: 100 with score 475.0

  

References

[1] Actor-Critic Algorithms Authors: Vijay R. Konda John N. Tsitsiklis Link: https://papers.nips.cc/paper/1786-actor-critic-algorithms.pdf

cartpole-v1-actor-critic-keras's Issues

TF 2.0 error

The example is not working with TF 2.0, because Session has been deprecated.