Deep-Reinforcement-Learning-for-Boardgames
Deep-Reinforcement-Learning-for-Boardgames copied to clipboard
Published
20 hours ago •
masus04
masus04
Implement JSRL like training strategy
This approach intends to make use of a prior strategy in order to unroll the game up to a certain point in time t, then let the exploration strategy being trained take over. t is then gradually reduced as the exploration strategy improves.
In order to generate game_state(t)s, we intend to perform the following steps:
- Choose a
prior strategythat can be configured to play deterministic or non-deterministic - Play the non-deterministic version of
prior strategyeither against itself or a deterministic version of itself up to timet - Determine which player is favoured according to the deterministic
prior strategy - Play the
exploration strategyagainst the deterministicprior strategy, playing as the favoured player in order to guarantee it has a chance of winning.
Blog post: https://ai.googleblog.com/2022/04/efficiently-initializing-reinforcement.html?m=1
