Meta Reinforcement Learning Experiments

• async - just a plain Actor Critic
• dqn - plain DQNetwork
• fun - implementation of FeUdal Networks for Hierarchical Reinforcement Learning (https://arxiv.org/abs/1703.01161)
• ga3c - implementation of GA3C: Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU (not finished)
• meta_bandits - meta learning experiments using bandit environments (2 arms dependent, 2 arms independent and 11 arms)
• meta_mdp - meta learning experiments using a simple MDP environment