k-tang-mkv / baserlalgorithm

Basic algorithms of reinforcement learning are implemented here

Goal

The goal of we train a agent is that we want the agent to play the game by itself until can find an appropriate way, i.e. a good policy, to play the game well.

How we train the agent?

Agent must find a good policy to survive by some algorithms or models. Basically, this is a control and optimization problem. We need control the agent so that it can consecutively optimize its algorithm until it acquires the best returns.

Basic elements

• Environments (envs)
• Policy
• Reward signal
• Value function
• Model
• ...

Algorithms

Tabular Solution Methods

• Dynamic Programming
• Monte Carlo Methods
• Temporal-Difference learning
• ...

Approximate Solution Methods

• DQN

References

• Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. A Bradford Book, Cambridge, MA, USA.
• Mnih, V., Kavukcuoglu, K., Silver, D. et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).
• Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M.A. (2013). Playing Atari with Deep Reinforcement Learning. ArXiv, abs/1312.5602.