论文标题
稀疏奖励目标条件学习的阶段性自我模拟减少
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
论文作者
论文摘要
将监督学习的力量（SL）朝着更有效的强化学习（RL）方法来实现了最近的趋势。我们通过交替在线RL和离线SL来解决稀疏奖励目标条件问题，提出一种新颖的阶段方法。在在线阶段，我们在离线阶段进行RL培训并收集推出数据，我们对数据集的这些成功轨迹执行SL。为了进一步提高样本效率，我们在在线阶段采用其他技术，包括减少任务以产生更可行的轨迹和基于价值的基于价值的内在奖励，以减轻稀疏的回报问题。我们称此总体算法为阶段性的自我模拟还原（Pair）。对稀疏的奖励目标机器人控制问题（包括具有挑战性的堆叠任务），对基本上优于非强调RL和Phasic SL基准。 Pair是第一个学会堆叠6个立方体，仅0/1成功奖励的RL方法。
It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic approach by alternating online RL and offline SL for tackling sparse-reward goal-conditioned problems. In the online phase, we perform RL training and collect rollout data while in the offline phase, we perform SL on those successful trajectories from the dataset. To further improve sample efficiency, we adopt additional techniques in the online phase including task reduction to generate more feasible trajectories and a value-difference-based intrinsic reward to alleviate the sparse-reward issue. We call this overall algorithm, PhAsic self-Imitative Reduction (PAIR). PAIR substantially outperforms both non-phasic RL and phasic SL baselines on sparse-reward goal-conditioned robotic control problems, including a challenging stacking task. PAIR is the first RL method that learns to stack 6 cubes with only 0/1 success rewards from scratch.
