pith. sign in

arxiv: 1707.01495 · v3 · pith:SFU4RE4Unew · submitted 2017-07-05 · 💻 cs.LG · cs.AI· cs.NE· cs.RO

Hindsight Experience Replay

classification 💻 cs.LG cs.AIcs.NEcs.RO
keywords experiencehindsightreplayrewardstaskbinarylearningsparse
0
0 comments X
read the original abstract

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum. We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in each case using only binary rewards indicating whether or not the task is completed. Our ablation studies show that Hindsight Experience Replay is a crucial ingredient which makes training possible in these challenging environments. We show that our policies trained on a physics simulation can be deployed on a physical robot and successfully complete the task.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning

    cs.AI 2026-05 unverdicted novelty 6.0

    SD-Search derives step-level supervision for search queries in reasoning agents via on-policy hindsight self-distillation using the policy as both student and teacher.

  2. Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    Ms.PR applies multi-scale predictive supervision to enforce goal-directed alignment in latent spaces for offline GCRL, yielding improved representation quality and performance on vision and state-based tasks.

  3. Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings

    cs.LG 2026-03 unverdicted novelty 6.0

    HAPO adds a hindsight-anchored SSI operator with Thompson gating to GRPO-style RLVR, achieving asymptotic consistency that recovers unbiased on-policy gradients as the policy improves.

  4. Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach

    cs.LG 2024-11 unverdicted novelty 6.0

    DIPPER uses bi-level optimization and DPO to train the higher-level policy from stationary preference comparisons and value regularization, claiming up to 40% gains on robotic navigation and manipulation tasks while i...

  5. Abstraction for Offline Goal-Conditioned Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 5.0

    Introduces relativised options and hierarchical abstraction to reuse experience across similar contexts in offline GCRL, with two algorithms demonstrating performance gains.

  6. SE-GA: Memory-Augmented Self-Evolution for GUI Agents

    cs.LG 2026-05 unverdicted novelty 5.0

    SE-GA combines Test-Time Memory Extension for dynamic context retrieval with Memory-Augmented Self-Evolution training to reach 89.0% on ScreenSpot and 75.8% on AndroidControl-High.

  7. Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning

    cs.RO 2025-10 unverdicted novelty 5.0

    A single goal-conditioned RL policy trained on contact plans performs multiple gaits and bimanual manipulation tasks on quadruped and humanoid robots.

  8. Gymnasium: A Standard Interface for Reinforcement Learning Environments

    cs.LG 2024-07 accept novelty 5.0

    Gymnasium establishes a standardized API for RL environments to improve interoperability, reproducibility, and ease of development in reinforcement learning.