Texas Hold’em No Limit
This environment is part of the classic environments. Please read that page first for general information.
| Name | Value |
|---|---|
| Actions | Discrete |
| Agents | 2 |
| Parallel API | false |
| Manual Control | No |
| Action Shape | Discrete(103) |
| Action Values | Discrete(103) |
| Observation Shape | (54,) |
| Observation Values | [0, 100] |
| Import | from pettingzoo.classic import texas_holdem_no_limit_v0 |
| Agents | agents= ['player_0', 'player_1'] |
Agent Environment Cycle
Texas Hold’em No Limit
Texas Hold’em No Limit is a variation of Texas Hold’em where there is no limit on the amount of each raise or the number of raises.
Our implementation wraps RLCard and you can refer to its documentation for additional details. Please cite their work if you use this game in research.
Observation Space
The observation space is similar to Texas Hold’em. The first 52 entries represent the union of the current player’s hand and the community cards.
| Index | Description | Values |
|---|---|---|
| 0 - 12 | Spades0: A, 1: 2, …, 12: K |
[0, 1] |
| 13 - 25 | Hearts13: A, 14: 2, …, 25: K |
[0, 1] |
| 26 - 38 | Diamonds26: A, 27: 2, …, 38: K |
[0, 1] |
| 39 - 51 | Clubs39: A, 40: 2, …, 51: K |
[0, 1] |
| 52 | Number of Chips of player_0 | [0, 100] |
| 53 | Number of Chips of player_1 | [0, 100] |
Action Space
| Action ID | Action |
|---|---|
| 0 | Call |
| 1 | Raise |
| 2 | Check |
| 3 - 102 | Raise3: 1 chip, 4: 2 chips, …, 102: 100 chips |
Rewards
| Winner | Loser |
|---|---|
| +raised chips/2 | -raised chips/2 |
Legal Moves
The legal moves available for each agent, found in env.infos[agent]['legal_moves'], are updated after each step. Taking an illegal move ends the game with a reward of -1 for the illegally moving agent and a reward of 0 for all other agents.