关于ICLR2022

In 2022, in an effort to broaden the diversity of the pool of participants to ICLR 2022, we are starting a program specifically assisting underrepresented, underprivileged, independent, and particularly first-time ICLR submitters. We hope this program can help create a path for prospective ICLR authors—who would not otherwise have considered participating in, or working on a submission to ICLR—to join the ICLR community, find project ideas, collaborators, mentorship and computational support throughout the submission process, and establish valuable connections and first-hand training during their early career.

Our goal is to provide underrepresented minorities, especially first-timers, and independent researchers, a taste of first-hand research experiences within a community, and a clear target to work towards. For that we need experienced researchers to join this program to provide starter ideas, ongoing feedback, lightweight mentorship, all the way to fully engaged collaboration.

重要时间节点

35. A First-Order Method for Estimating Natural Gradients for Variational Inference with Gaussians and Gaussian Mixture Models

58. The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program

83. Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

122. SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

154. CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation

155. Reasoning With Hierarchical Symbols: Reclaiming Symbolic Policies For Visual Reinforcement Learning

156. Distributional Perturbation for Efficient Exploration in Distributional Reinforcement Learning

157. PDQN - A Deep Reinforcement Learning Method for Planning with Long Delays: Optimization of Manufacturing Dispatching

168. Occupy & Specify: Investigations into a Maximum Credit Assignment Occupancy Objective for Data-efficient Reinforcement Learning

185. Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities

225. Pareto Policy Adaptation

226. Differentially Private SGD with Sparse Gradients

227. A Principled Permutation Invariant Approach to Mean-Field Multi-Agent Reinforcement Learning

228. Neural Combinatorial Optimization with Reinforcement Learning : Solving theVehicle Routing Problem with Time Windows

282. Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling

318. An Improved Composite Functional Gradient Learning by Wasserstein Regularization for Generative adversarial networks

356. Which model to trust: assessing the influence of models on the performance of reinforcement learning algorithms for continuous control tasks

381. On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning

427. Unsupervised fashion for controllable generations: A manifold control of latent feature using contrastive alignment and self-organizing rewards

428. Recommending Actions to Improve Engagement for Diabetes Management using Off-Policy Learning

429. Policy Advantage Networks

448. Foresight Constrained Subgoal Space for Hierarchical Reinforcement Learning via Local Imagination and Evolutionary Probing

455. Research on fusion algorithm of multi-attribute decision making and reinforcement learning based on intuitionistic fuzzy number in wargame environment

关于ICLR2022

重要时间节点

提交论文列表

1. Learning Sampling Policy for Faster Derivative Free Optimization

2. IA-MARL: Imputation Assisted Multi-Agent Reinforcement Learning for Missing Training Data

3. Pessimistic Model Selection for Offline Deep Reinforcement Learning

4. Robust Imitation via Mirror Descent Inverse Reinforcement Learning

5. Optimizing Few-Step Diffusion Samplers by Gradient Descent

6. Offline Pre-trained Multi-Agent Decision Transformer

7. Tesseract: Gradient Flip Score to Secure Federated Learning against Model Poisoning Attacks

8. DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

9. Skill-based Meta-Reinforcement Learning

10. Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach

11. Faster Reinforcement Learning with Value Target Lower Bounding

12. On Distributed Adaptive Optimization with Gradient Compression

13. Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning

14. DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck

15. An Experimental Design Perspective on Exploration in Reinforcement Learning

16. Zero-Shot Reward Specification via Grounded Natural Language

17. Coordinated Attacks Against Federated Learning: A Multi-Agent Reinforcement Learning Approach

18. Generalisation in Lifelong Reinforcement Learning through Logical Composition

19. Distributional Reinforcement Learning with Monotonic Splines

20. Learning Pseudometric-based Action Representations for Offline Reinforcement Learning

21. Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

22. Programmatic Reinforcement Learning without Oracles

23. Containerized Distributed Value-Based Multi-Agent Reinforcement Learning

24. PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

25. Bi-linear Value Networks for Multi-goal Reinforcement Learning

26. Pareto Policy Pool for Model-based Offline Reinforcement Learning

27. Resmax: An Alternative Soft-Greedy Operator for Reinforcement Learning

28. A Simple Reward-free Approach to Constrained Reinforcement Learning

29. Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning

30. The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning

31. COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

32. Spatially and Seamlessly Hierarchical Reinforcement Learning for State Space and Policy Space in Autonomous Driving

33. Stochastic Reweighted Gradient Descent

34. EqR: Equivariant Representations for Data-Efficient Reinforcement Learning

35. A First-Order Method for Estimating Natural Gradients for Variational Inference with Gaussians and Gaussian Mixture Models

36. Reinforcement Learning with Predictive Consistent Representations

37. Offline-Online Reinforcement Learning: Extending Batch and Online RL

38. DisTop: Discovering a Topological representation to learn diverse and rewarding skills

39. OVD-Explorer: A General Information-theoretic Exploration Approach for Reinforcement Learning

40. LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning

41. Projective Manifold Gradient Layer for Deep Rotation Regression

42. Learning Invariant Reward Functions through Trajectory Interventions

43. A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning

44. Reachability Traces for Curriculum Design in Reinforcement Learning

45. When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?

46. The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

47. EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning

48. A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks

49. The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

50. Finding General Equilibria in Many-Agent Economic Simulations using Deep Reinforcement Learning

51. Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates

52. Accelerated Policy Learning with Parallel Differentiable Simulation

53. Learning Transferable Reward for Query Object Localization with Policy Adaptation

54. A Risk-Sensitive Policy Gradient Method

55. Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks

56. Know Your Action Set: Learning Action Relations for Reinforcement Learning

57. Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos

58. The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program

59. Variational Wasserstein gradient flow

60. GradMax: Growing Neural Networks using Gradient Information

61. SPLID: Self-Imitation Policy Learning through Iterative Distillation

62. Goal Randomization for Playing Text-based Games without a Reward Function

63. Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?

64. Second-Order Rewards For Successor Features

65. StARformer: Transformer with State-Action-Reward Representations

66. Data Sharing without Rewards in Multi-Task Offline Reinforcement Learning

67. MixRL: Data Mixing Augmentation for Regression using Reinforcement Learning

68. Safety-aware Policy Optimisation for Autonomous Racing

69. Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

70. Low-Precision Stochastic Gradient Langevin Dynamics

71. Autonomous Reinforcement Learning: Formalism and Benchmarking

72. Gradient Assisted Learning

73. A Boosting Approach to Reinforcement Learning

74. Should I Run Offline Reinforcement Learning or Behavioral Cloning?

75. Disentangling Generalization in Reinforcement Learning

76. Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction

77. Variance Reduced Domain Randomization for Policy Gradient