@nikg4 @taenin what other functions should we put into the GrpoRewards struct? other rewards functions? Here is a first cut from sonnet
- Shaping Functions:
potential_based_shaping(state, next_state, gamma) - Implement potential-based reward shaping
curiosity_reward(state, next_state, prediction) - Generate intrinsic motivation rewards
constraint_penalty(state, action) - Apply penalties for constraint violations
Implement potential_based_shaping, curiosity_reward, constraint_penalty functions
Originally posted by @kyjohnso in #13