RL-Algorithms

Resources used are listen in each ipynb file

The ES + A2C shows early convergence and also more stability over episodes.

The ES algorithm used is from Evolution-Guided Policy Gradient in Reinforcement Learning - https://arxiv.org/abs/1805.07917

Implementating preliminary RL Algoirthms:

1. DQN (https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf)
2. Sample Efficient Actor-Critic with Experience Replay (https://arxiv.org/abs/1611.01224)
3. Evolutionary Strategies (https://arxiv.org/abs/1703.03864)