# Overcoming Exploration in Reinforcement Learning with Demonstrations

arXiv: https://arxiv.org/abs/1709.10089 · HTML: https://mlsanity.com/paper/1709.10089/

## Key facts

- Cited by 340 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2017.

## Built on by (most cited first, 30 of 340)

- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Reward learning from human preferences and demonstrations in Atari](https://mlsanity.com/paper/1811.06521/) (2018)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [Exploration in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2205.00824/) (2022)
- [Goal-conditioned Imitation Learning](https://mlsanity.com/paper/1906.05838/) (2019)
- [Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient](https://mlsanity.com/paper/2210.06718/) (2022)
- [Goal-Conditioned Reinforcement Learning: Problems and Solutions](https://mlsanity.com/paper/2201.08299/) (2022)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation](https://mlsanity.com/paper/2403.03949/) (2024)
- [Self-Imitation Learning](https://mlsanity.com/paper/1806.05635/) (2018)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Jump-Start Reinforcement Learning](https://mlsanity.com/paper/2204.02372/) (2022)
- [Policy Expansion for Bridging Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2302.00935/) (2023)
- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video](https://mlsanity.com/paper/2202.00164/) (2022)
- [Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL](https://mlsanity.com/paper/2202.04478/) (2022)
- [Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation](https://mlsanity.com/paper/2105.14829/) (2021)
- [Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks](https://mlsanity.com/paper/2110.03655/) (2021)
- [Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention](https://mlsanity.com/paper/1812.04155/) (2018)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations](https://mlsanity.com/paper/2303.01497/) (2023)
- [Offline Learning from Demonstrations and Unlabeled Experience](https://mlsanity.com/paper/2011.13885/) (2020)
- [Asymmetric self-play for automatic goal discovery in robotic manipulation](https://mlsanity.com/paper/2101.04882/) (2021)
- [Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model](https://mlsanity.com/paper/2412.13630/) (2024)
- [Watch and Match: Supercharging Imitation with Regularized Optimal Transport](https://mlsanity.com/paper/2206.15469/) (2022)
- [Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress](https://mlsanity.com/paper/2206.01626/) (2022)

## Abstract (arXiv)

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm. Our method, which builds on top of Deep Deterministic Policy Gradients and Hindsight Experience Replay, provides an order of magnitude of speedup over RL on simulated robotics tasks. It is simple to implement and makes only the additional assumption that we can collect a small set of demonstrations. Furthermore, our method is able to solve tasks not solvable by either RL or behavior cloning alone, and often ends up outperforming the demonstrator policy.