[FEATURE] Implement self-play for two-player zero-sum games

[RPegoud]

Issue: #99

Description: Add self-play versions of DQN and PPO for two-player zero-sum games in PGX environments.

Checklist:

• [x] Determine how to keep the value estimation consistent (e.g. flip the board, use a negative discount)
• [x] Add PGX environment configs
• [ ] Implement self-play for DQN
• [ ] And for PPO
• [ ] (optional) If possible, for AlphaZero