feature(pu/zt): add 2048 env and Stochastic MuZero

[puyuan1996]

• add stochastic muzero ptree and ctree, policy, model
• add 2048 env and unittest
• add 2048 bot
• add 2048 related configs

• The benchmark results in the 2048 environment:

• The render video to illustrate the performance of Random action, Bot action, MuZero, and Stochastic MuZero agents in the 2048 environment.

  • Random action (~1000):
    

  • Bot action (~30000-70000):
    

  • MuZero sim=100 (~27956):
    

  • Stochastic MuZero sim=100 (~37356）:
    

  • Where the term sim represents the number of simulations used for evaluation in MCTS, and the score within brackets corresponds to the score procured by each respective agent.

#41