Pinned Loading

1. liuqh16/LAG liuqh16/LAG Public

   An environment based on JSBSIM aimed at one-to-one close air combat.

   Python 424 124

2. RPBT RPBT Public

   (AAAI24 oral) Implementation of RPPO(Risk-sensitive PPO) and RPBT(Population-based self-play with RPPO)

   Python 12 1

3. ETD ETD Public

   Episodic Novelty Through Temporal Distance (ICLR 2025)

   Python 6

4. Policy-As-GenVerifier Policy-As-GenVerifier Public

   Implementation of "PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier"

   Python 11 1

5. RS-GRPO RS-GRPO Public

   Risk-Sensitive GRPO algorithm

   Python 4