Data to 7 Oct 2026

Parrot: Data-Driven Behavioral Priors for Reinforcement Learning

arXiv 2011.10024 ↗First posted 19 Nov 2020cs.LG cs.ROcited by 136

Not on the map. Why?

Cited by 42 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language processing or computer vision, pre-training on large, previously collected datasets to bootstrap learning for new tasks has emerged as a powerful paradigm to reduce data requirements when learning a new task. In this paper, we ask the following question: how can we enable similarly useful pre-training for RL agents? We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials from a wide range of previously seen tasks, and we show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors. We demonstrate the effectiveness of our approach in challenging robotic manipulation domains involving image observations and sparse reward functions, where our method outperforms prior works by a substantial margin.

Key facts. Cited by 136 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 36; 2023: 31; 2024: 18; 2025: 13; 2026: 18.

136 papers.

Sort:

By area:

2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
2022Behavior Transformers: Cloning k modes with one stonecited by 299
2023Imitating Human Behaviour with Diffusion Modelscited by 260
2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
2021Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemblecited by 211
2022Offline Reinforcement Learning via High-Fidelity Generative Behavior Modelingcited by 177
2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 169
2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
2024Behavior Generation with Latent Actionscited by 159
2025Steering Your Diffusion Policy with Latent Space Reinforcement Learningcited by 149
2023Policy Representation via Diffusion Probability Model for Reinforcement Learningcited by 105
2022From Play to Policy: Conditional Behavior Generation from Uncurated Robot Datacited by 103

38 more

2023Policy Expansion for Bridging Offline-to-Online Reinforcement Learningcited by 103
2025Reinforcement Learning with Action Chunkingcited by 97
2021Representation Matters: Offline Pretraining for Sequential Decision Makingcited by 90
2022Latent Plans for Task-Agnostic Offline Reinforcement Learningcited by 81
2024From Imitation to Refinement -- Residual RL for Precise Assemblycited by 80
2022Can Wikipedia Help Offline Reinforcement Learning?cited by 76
2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 75
2023XSkill: Cross Embodiment Skill Discoverycited by 74
2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 73
2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 63
2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 56
2023Diffusion Reward: Learning Rewards via Conditional Video Diffusioncited by 56
2022Learning Neuro-Symbolic Skills for Bilevel Planningcited by 55
2022Dichotomy of Control: Separating What You Can Control from What You Cannotcited by 47
2021Learning Neuro-Symbolic Relational Transition Models for Bilevel Planningcited by 43
2021TRAIL: Near-Optimal Imitation Learning with Suboptimal Datacited by 39
2021Hierarchical Few-Shot Imitation with Skill Transition Modelscited by 37
2022Spectral Decomposition Representation for Reinforcement Learningcited by 35
2023Beyond Reward: Offline Preference-guided Policy Optimizationcited by 35
2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
2021Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedbackcited by 34
2026Q-learning with Adjoint Matchingcited by 33
2022Choreographer: Learning and Adapting Skills in Imaginationcited by 31
2022DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systemscited by 27
2021Learning Transferable Motor Skills with Hierarchical Latent Mixture Policiescited by 26
2024FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learningcited by 26
2021Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RLcited by 24
2023SPRINT: Scalable Policy Pre-Training via Language Instruction Relabelingcited by 24
2022Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Roboticscited by 23
2021Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Modelscited by 22
2022Learning Options via Compressioncited by 22
2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 22
2021Continuous Control with Action Quantization from Demonstrationscited by 21
2022Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flowscited by 21
2023Accelerating Exploration with Unlabeled Prior Datacited by 21
2023Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Datacited by 19
2022Pretraining in Deep Reinforcement Learning: A Surveycited by 18

50 most cited of 136 All 136 (JSON)