Can I add expert data to the replay buffer used by the DDPG algorithm in order to make it converge faster?
Appropriate algorithm for RL problem with sparse rewards, continuous actions and significant stochasticity
Why is the behaviour policy denoted by $\beta$ and the exploration policy by $ \mu'$ in the DDPG paper?
Are there examples of agents that use a more modest number of parameters on Pendulum (or similar environments)?
Only top scored, non community-wiki answers of a minimum length are eligible