paper-with-me

Papers

Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning

2022-06-24 · Yunfei Li, Tian Gao, Jiaqi Yang, Huazhe Xu, Yi Wu

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.

📄 PDF Abstract BibTeX arXiv:2206.12030

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Residual Q-Learning: Offline and Online Policy Customization without Value

2023-06-15 · NeurIPS 2023 11 · Chenran Li, Chen Tang, Haruki Nishimura, Jean Mercat 외

Imitation Learning (IL) is a widely used framework for learning imitative behavior from demonstrations. It is especially appealing for solving complex real-world tasks where handcrafting reward function is difficult, or …

Imitation LearningQ-Learning

Deep Imitative Models for Flexible Inference, Planning, and Control

2018-10-15 · ICLR 2020 1 · Nicholas Rhinehart, Rowan Mcallister, Sergey Levine

Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and rewar…

Autonomous DrivingImitation Learning

Aphasic Speech Recognition using a Mixture of Speech Intelligibility Experts

2020-08-25

Robust speech recognition is a key prerequisite for semantic feature extraction in automatic aphasic speech analysis. However, standard one-size-fits-all automatic speech recognition models perform poorly when applied to…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Mixture-of-ExpertsRobust Speech Recognition+2

Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning

2025-03-03 · Adrià López Escoriza, Nicklas Hansen, Stone Tao, Tongzhou Mu 외

Long-horizon tasks in robotic manipulation present significant challenges in reinforcement learning (RL) due to the difficulty of designing dense reward functions and effectively exploring the expansive state-action spac…

Reinforcement Learning (RL)

Solving Compositional Reinforcement Learning Problems via Task Reduction

2021-03-13 · ICLR 2021 1 · Yunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang 외

We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems. SIR is based on two core ideas: task reduction and self-imitation. Task reduction tackl…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1