We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| shreyassr123/multi-step-markov-games | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| find_minimax_value | Ran | shreyassr123/multi-step-markov-games/SubsectionB/Code_for_Table2_Table3.py pointer only (licence: NONE) · get_code("040b250517fba6ef") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
An interesting iterative procedure is proposed to solve a two-player zero-sum Markov games. Under suitable assumption, the boundedness of the proposed iterates is obtained theoretically. Using results from stochastic approximation, the almost sure convergence of the proposed two-step minimax Q-learning is obtained theoretically. More specifically, the proposed algorithm converges to the game theoretic optimal value with probability one, when the model information is not known. Numerical simulation authenticate that the proposed algorithm is effective and easy to implement.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.04240")
get_code_for_paper("2407.04240")
have("2407.04240")
Connect an agent — have() is free.