Algorithms

Use these references when you need the objective, scope, and implementation notes for a supported RL algorithm.

Algorithm	Summary
PPO	Proximal Policy Optimization.
GRPO	Group Relative Policy Optimization.
DAPO	Decoupled-clip and dynamic-sampling policy optimization.
Reinforce++	An enhanced REINFORCE baseline.
SAC	Soft Actor-Critic.
CrossQ	Sample-efficient off-policy RL without target networks.
RLPD	RL with prior data.
IQL	Implicit Q-Learning for offline RL.
Async PPO	Asynchronous, pipelined PPO.