mlsanityData to 7 Oct 2026

Beating Atari with Natural Language Guided Reinforcement Learning

arXiv 1704.05539 ↗First posted 18 Apr 2017cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

We introduce the first deep reinforcement learning agent that learns to beat Atari games with the aid of natural language instructions. The agent uses a multimodal embedding between environment observations and natural language to self-monitor progress through a list of English instructions, granting itself reward for completing instructions in addition to increasing the game score. Our agent significantly outperforms Deep Q-Networks (DQNs), Asynchronous Advantage Actor-Critic (A3C) agents, and the best agents posted to OpenAI Gym on what is often considered the hardest Atari 2600 environment: Montezuma's Revenge.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 5; 2022: 5; 2023: 4; 2024: 5; 2025: 3; 2026: 1.

24 papers.

Sort:

By area:

  1. 2023Training Language Models with Language Feedback at Scalecited by 125
  2. 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 117
  3. 2022Training Language Models with Language Feedbackcited by 48
  4. 2020Learning Rewards from Linguistic Feedbackcited by 41
  5. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  6. 2021Zero-shot Task Adaptation using Natural Languagecited by 15
  7. 2022Transformers are Adaptable Task Plannerscited by 15
  8. 2024A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedbackcited by 9
  9. 2024The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewardscited by 7
  10. 2022E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidancecited by 6
  11. 2023Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imaginationcited by 6
  12. 2022SMLT: A Serverless Framework for Scalable and Adaptive Machine Learning Design and Trainingcited by 4
12 more
  1. 2024Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Modelscited by 4
  2. 2025Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigationcited by 4
  3. 2023Language-guided Task Adaptation for Imitation Learningcited by 2
  4. 2023A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agentscited by 2
  5. 2025DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learningcited by 1
  6. 2021Grounding Complex Navigational Instructions Using Scene Graphscited by 0
  7. 2021Reinforcement Learning with Information-Theoretic Actuationcited by 0
  8. 2022Knowledge-Integrated Informed AI for National Securitycited by 0
  9. 2024Effective Reward Specification in Deep Reinforcement Learningcited by 0
  10. 2024From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learningcited by 0
  11. 2025HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agentscited by 0
  12. 2026Cooperative-Competitive Team Play of Real-World Craft Robotscited by 0