pith. sign in

Balaraman Ravindran

Identifiers

  • name variant Balaraman Ravindran 0.60 · backfill

Papers (39)

  1. How Much Online RL is Enough? Informative Rollouts for Offline Preference Optimization in RLVR cs.LG · 2026 · author #2
  2. PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment cs.LG · 2026 · author #4
  3. Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics cs.LG · 2026 · author #2
  4. Generalized Random Surfer-Pair Models cs.SI · 2019 · author #2
  5. MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning cs.LG · 2019 · author #3
  6. Successor Options: An Option Discovery Framework for Reinforcement Learning cs.LG · 2019 · author #3
  7. Network Representation Learning: Consolidation and Renewed Bearing cs.LG · 2019 · author #11
  8. Edge Replacement Grammars: A Formal Language Approach for Generating Graphs cs.SI · 2019 · author #3
  9. Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning cs.SD · 2019 · author #2
  10. Hypergraph Clustering: A Modularity Maximization Approach cs.LG · 2018 · author #5
  11. Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning cs.LG · 2018 · author #4
  12. Improvements on Hindsight Learning cs.LG · 2018 · author #4
  13. Fusion Graph Convolutional Networks cs.LG · 2018 · author #5
  14. HOPF: Higher Order Propagation Framework for Deep Collective Classification cs.LG · 2018 · author #5
  15. Language Expansion In Text-Based Games cs.CL · 2018 · author #4
  16. DiGrad: Multi-Task Reinforcement Learning with Shared Actions cs.LG · 2018 · author #5
  17. Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks cs.CV · 2018 · author #4
  18. Rate of Change Analysis for Interestingness Measures cs.LG · 2017 · author #4
  19. Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates cs.LG · 2017 · author #4
  20. Shared Learning : Enhancing Reinforcement in $Q$-Ensembles cs.LG · 2017 · author #2
  21. RAIL: Risk-Averse Imitation Learning cs.LG · 2017 · author #3
  22. Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning cs.LG · 2017 · author #4
  23. Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning cs.LG · 2017 · author #4
  24. Diversity driven Attention Model for Query-based Abstractive Summarization cs.CL · 2017 · author #4
  25. Thresholding Bandits with Augmented UCB cs.LG · 2017 · author #4
  26. DyVEDeep: Dynamic Variable Effort Deep Neural Networks cs.NE · 2017 · author #3
  27. Learning to Multi-Task by Active Sampling cs.NE · 2017 · author #4
  28. Exploration for Multi-task Reinforcement Learning with Deep Generative Models cs.AI · 2016 · author #3
  29. EPOpt: Learning Robust Neural Network Policies Using Model Ensembles cs.LG · 2016 · author #3
  30. HEMI: Hyperedge Majority Influence Maximization cs.SI · 2016 · author #2
  31. Linear Bandit algorithms using the Bootstrap stat.ML · 2016 · author #2
  32. Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning cs.CL · 2015 · author #4
  33. TSEB: More Efficient Thompson Sampling for Policy Learning cs.LG · 2015 · author #3
  34. A Reinforcement Learning Approach to Online Learning of Decision Trees cs.LG · 2015 · author #4
  35. Correlational Neural Networks cs.CL · 2015 · author #4
  36. Scalable Positional Analysis for Studying Evolution of Nodes in Networks cs.SI · 2014 · author #2
  37. An Autoencoder Approach to Learning Bilingual Word Representations cs.CL · 2014 · author #5
  38. Efficient Computation of the Shapley Value for Game-Theoretic Network Centrality cs.GT · 2014 · author #4
  39. Fractional Moments on Bandit Problems cs.LG · 2012 · author #2

Mentions

  • 1510.03519 #4 · backfill · confidence 0.70 Balaraman Ravindran
  • 1510.02874 #3 · backfill · confidence 0.70 Balaraman Ravindran
  • 1507.06923 #4 · backfill · confidence 0.70 Balaraman Ravindran
  • 2602.12643 #2 · arxiv_oai · confidence 0.70 Balaraman Ravindran
  • 1504.07225 #4 · backfill · confidence 0.70 Balaraman Ravindran
  • 1402.3797 #2 · backfill · confidence 0.70 Balaraman Ravindran
  • 1402.1454 #5 · backfill · confidence 0.70 Balaraman Ravindran
  • 1402.0567 #4 · backfill · confidence 0.70 Balaraman Ravindran
  • 1202.3750 #2 · backfill · confidence 0.70 Balaraman Ravindran
  • 2605.21266 #2 · arxiv_oai · confidence 0.70 Balaraman Ravindran
  • 2605.21225 #4 · arxiv_oai · confidence 0.70 Balaraman Ravindran

Frequent Coauthors