AAAI 2020 accepted papers on Reinforcement learning
69 of the 1,610 papers accepted at AAAI 2020 (4.3%) are on Reinforcement learning, compared with 5.0% at AAAI 2019. They fall into 6 topics.
See AAAI 2020 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Visual and representation RL · 22 papers
- Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control (458 citations)
- Exploratory Combinatorial Optimization with Reinforcement Learning (186 citations)
- MetaLight: Value-Based Meta-Reinforcement Learning for Traffic Signal Control (177 citations)
- Adaptive Quantitative Trading: An Imitative Deep Reinforcement Learning Approach (151 citations)
- Learning to Optimize Variational Quantum Circuits to Solve Combinatorial Problems (129 citations)
- Reinforcement Learning with Perturbed Rewards (127 citations)
- Tree-Structured Policy Based Progressive Reinforcement Learning for Temporally Language Grounding in Video (126 citations)
- Proximal Distilled Evolutionary Reinforcement Learning (84 citations)
- Reinforcement Learning Based Meta-Path Discovery in Large-Scale Heterogeneous Information Networks (47 citations)
- Hierarchical Reinforcement Learning for Open-Domain Dialog (37 citations)
- Dynamic Reward-Based Dueling Deep Dyna-Q: Robust Policy Learning in Noisy Environments (33 citations)
- Dialog State Tracking with Reinforced Data Augmentation (26 citations)
and 10 more in the interactive map.
Policy gradient and actor-critic · 17 papers
- IPO: Interior-Point Policy Optimization under Constraints (163 citations)
- Discretizing Continuous Action Space for On-Policy Optimization (115 citations)
- Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs (100 citations)
- Attentive Experience Replay (58 citations)
- Options of Interest: Temporal Abstraction with Interest Functions (25 citations)
- Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning (23 citations)
- Cost-Effective Incentive Allocation via Structured Counterfactual Inference (19 citations)
- Gradient-Aware Model-Based Policy Search (18 citations)
- Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization (15 citations)
- On the Role of Weight Sharing During Deep Option Learning (15 citations)
- Deep Conservative Policy Iteration (10 citations)
- Gamma-Nets: Generalizing Value Estimation over Timescale (8 citations)
and 5 more in the interactive map.
MDPs and planning · 14 papers
- Count-Based Exploration with the Successor Representation (121 citations)
- Scalable Methods for Computing State Similarity in Deterministic Markov Decision Processes (78 citations)
- Reinforcement Learning with Non-Markovian Rewards (72 citations)
- Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents (71 citations)
- Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy (42 citations)
- Off-Policy Evaluation in Partially Observable Environments (36 citations)
- Point-Based Methods for Model Checking in Partially Observable Markov Decision Processes (28 citations)
- Lifelong Learning with a Changing Action Set (22 citations)
- An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies (15 citations)
- Planning with Abstract Learned Models While Learning Transferable Subtasks (10 citations)
- Reinforcement Learning When All Actions Are Not Always Available (8 citations)
- Querying to Find a Safe Policy under Uncertain Safety Constraints in Markov Decision Processes (6 citations)
and 2 more in the interactive map.
Imitation learning · 9 papers
- Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same Context (155 citations)
- Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic Diagnosis (67 citations)
- Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance (62 citations)
- Few-Shot Bayesian Imitation Learning with Logical Program Policies (32 citations)
- The Unreasonable Effectiveness of Inverse Reinforcement Learning in Advancing Cancer Research (15 citations)
- Variational Adversarial Kernel Learned Imitation Learning (8 citations)
- Learning from Interventions Using Hierarchical Policies for Safe Learning (7 citations)
- Deep Bayesian Nonparametric Learning of Rules and Plans from Demonstrations with a Learned Automaton Prior (6 citations)
- Adversarial Fence Patrolling: Non-Uniform Policies for Asymmetric Environments (4 citations)
RL from feedback · 4 papers
- What Makes A Good Story? Designing Composite Rewards for Visual Storytelling (62 citations)
- Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards (15 citations)
- What Is It You Really Want of Me? Generalized Reward Learning with Biased Beliefs about Domain Dynamics (6 citations)
- AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses (3 citations)
