mlsanityData to 7 Oct 2026

Representation-Driven Reinforcement Learning

arXiv 2305.19922 ↗First posted 31 May 2023cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly, embedding a policy network into a linear feature space allows us to reframe the exploration-exploitation problem as a representation-exploitation problem, where good policy representations enable optimal exploration. We demonstrate the effectiveness of this framework through its application to evolutionary and policy gradient-based approaches, leading to significantly improved performance compared to traditional methods. Our framework provides a new perspective on reinforcement learning, highlighting the importance of policy representation in determining optimal exploration-exploitation strategies.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

25 of 54 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  5. 2015Continuous control with deep reinforcement learningcited by 3,279
  6. 2015Trust Region Policy Optimizationcited by 2,503
  7. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  8. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  9. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  10. 2016Successor Features for Transfer in Reinforcement Learningcited by 331
  11. 2018Visual Reinforcement Learning with Imagined Goalscited by 248
  12. 2020Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oraclescited by 195
13 more
  1. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  2. 2023Equivariant Architectures for Learning in Deep Weight Spacescited by 106
  3. 2018Evolution-Guided Policy Gradient in Reinforcement Learningcited by 78
  4. 2018Simple random search provides a competitive approach to reinforcement learningcited by 75
  5. 2019Learning Action Representations for Reinforcement Learningcited by 75
  6. 2020Neural Contextual Bandits with Deep Representation and Shallow Explorationcited by 71
  7. 2021Neural Contextual Bandits without Regretcited by 40
  8. 2019The Natural Language of Actionscited by 28
  9. 2019Distributional Policy Optimization: An Alternative Approach for Continuous Controlcited by 21
  10. 2021Online Limited Memory Neural-Linear Bandits with Likelihood Matchingcited by 14
  11. 2022ERL-Re2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representationcited by 11
  12. 2021Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learningcited by 10
  13. 2019Language is Power: Representing States Using Natural Language in Reinforcement Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024Embedding-Aligned Language Modelscited by 9
  2. 2025Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spacescited by 7
  3. 2025Spectral Bellman Method: Unifying Representation and Exploration in RLcited by 3
  4. 2025Distributions as Actions: A Unified Framework for Diverse Action Spacescited by 0