← Back to Benchmarks
simmediumroboticsmetric · varies
D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay for Stable Reinforcement Learning in Robotic Manipulation
Description
Robotic manipulation remains challenging for reinforcement learning due to contact-rich dynamics, long horizons, and training instability. Although off-policy actor-critic algorithms such as SAC and TD3 perform well in simulation, they often suffer from policy oscillations and performance collapse in realistic settings, partly due to experience replay strategies that ignore the differing data requirements of the actor and the critic. We propose D-SPEAR: Dual-Stream Prioritized Experience Adaptiv