Toy Text
Toy Text environments are finite Markov decision processes with u32 discrete actions. Grid states are row-major integers; Blackjack uses a MultiDiscrete observation.
| Environment | State space | Actions | Default horizon |
|---|---|---|---|
| Blackjack | MultiDiscrete([32,11,2]) | 2 | none |
| CliffWalking | Discrete(nrow*ncol) | 4 | 100 |
| FrozenLake | Discrete(rows*cols) | 4 | 100 |
| Taxi | Discrete(500) | 6 | 200 |