Replay across Experiments: A Natural Extension of Off-Policy RL.
Dhruva TirumalaThomas LampeJosé Enrique ChenTuomas HaarnojaSandy H. HuangGuy LeverBen MoranTim HertweckLeonard HasencleverMartin A. RiedmillerNicolas HeessMarkus WulfmeierPublished in: ICLR (2024)