Maximum Entropy Hindsight Experience Replay
This work addresses incremental improvements in reinforcement learning for specific goal-based tasks, such as Predator-Prey environments.
The paper tackled improving the PPO-HER algorithm for goal-based reinforcement learning by selectively applying hindsight experience replay in a principled manner, resulting in enhanced performance in Predator-Prey environments.
Hindsight experience replay (HER) is well-known to accelerate goal-based reinforcement learning (RL). While HER is generally applied to off-policy RL algorithms, we previously showed that HER can also accelerate on-policy algorithms, such as proximal policy optimization (PPO), for goal-based Predator-Prey environments. Here, we show that we can improve the previous PPO-HER algorithm by selectively applying HER in a principled manner.