Workshop
Fri Dec 09 08:25 AM -- 05:35 PM (PST) @ Virtual None
Deep Reinforcement Learning Workshop
[ Contact: deeprl.workshop.neurips2022@gmail.com ]
In recent years, the use of deep neural networks as function approximators has enabled researchers to extend reinforcement learning techniques to solve increasingly complex control tasks. The emerging field of deep reinforcement learning has led to remarkable empirical results in rich and varied domains like robotics, strategy games, and multi-agent interactions. This workshop will bring together researchers working at the intersection of deep learning and reinforcement learning, and it will help interested researchers outside of the field gain a high-level view about the current state of the art and potential directions for future contributions.
| Opening Remarks | |
| Tobias Gerstenberg (Invited Talk) | |
| ESCHER: ESCHEWING IMPORTANCE SAMPLING IN GAMES BY COMPUTING A HISTORY VALUE FUNCTION TO ESTIMATE REGRET (Poster) | |
| Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training (Poster) | |
| Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function (Poster) | |
| Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes (Poster) | |
| Jakob Foerster (Invited Talk) | |
| Scientific Experiments in Reinforcement Learning (Opinion Talk) | |
| Transformers are Sample-Efficient World Models (Poster) | |
| Scaling Laws for a Multi-Agent Reinforcement Learning Model (Poster) | |
| Natasha Jaques (Opinion Talk) | |
| The World is not Uniformly Distributed; Important Implications for Deep RL (Opinion Talk) | |
| Amy Zhang (Invited Talk) | |
| Igor Mordatch (Invited Talk) | |
| John Schulman (Implementation Talk) | |
| Danijar Hafner (Implementation Talk) | |
| Kristian Hartikainen (Implementation Talk) | |
| Ilya Kostrikov, Aviral Kumar (Implementation Talk) | |
| Panel Discussion | |
| Closing Remarks | |
| Distance-Sensitive Offline Reinforcement Learning (Poster) | |
| Language Models Can Teach Themselves to Program Better (Poster) | |
| Graph Q-Learning for Combinatorial Optimization (Poster) | |
| Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL Environments (Poster) | |
| CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration (Poster) | |
| Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement (Poster) | |
| A Ranking Game for Imitation Learning (Poster) | |
| Distributional deep Q-learning with CVaR regression (Poster) | |
| Concept-based Understanding of Emergent Multi-Agent Behavior (Poster) | |
| Constrained Imitation Q-learning with Earth Mover’s Distance reward (Poster) | |
| SoftTreeMax: Policy Gradient with Tree Search (Poster) | |
| Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation (Poster) | |
| Hypernetwork-PPO for Continual Reinforcement Learning (Poster) | |
| DRL-EPANET: Deep reinforcement learning for optimal control at scale in Water Distribution Systems (Poster) | |
| Actor Prioritized Experience Replay (Poster) | |
| Converging to Unexploitable Policies in Continuous Control Adversarial Games (Poster) | |
| A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning (Poster) | |
| Training graph neural networks with policy gradients to perform tree search (Poster) | |
| Co-Imitation: Learning Design and Behaviour by Imitation (Poster) | |
| Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning (Poster) | |
| PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm (Poster) | |
| Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning (Poster) | |
| Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning (Poster) | |
| Guided Skill Learning and Abstraction for Long-Horizon Manipulation (Poster) | |
| Sample-efficient Adversarial Imitation Learning (Poster) | |
| PCRL: Priority Convention Reinforcement Learning for Microscopically Sequencable Multi-agent Problems (Poster) | |
| Robust Option Learning for Adversarial Generalization (Poster) | |
| Biological Neurons vs Deep Reinforcement Learning: Sample efficiency in a simulated game-world (Poster) | |
| Inducing Functions through Reinforcement Learning without Task Specification (Poster) | |
| Supervised Q-Learning for Continuous Control (Poster) | |
| Informative rewards and generalization in curriculum learning (Poster) | |
| EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model (Poster) | |
| MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations (Poster) | |
| Do As You Teach: A Multi-Teacher Approach to Self-Play in Deep Reinforcement Learning (Poster) | |
| Visual Reinforcement Learning with Self-Supervised 3D Representations (Poster) | |
| One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation (Poster) | |
| Skill Machines: Temporal Logic Composition in Reinforcement Learning (Poster) | |
| Deep Learning of Intrinsically Motivated Options in the Arcade Learning Environment (Poster) | |
| Policy Architectures for Compositional Generalization in Control (Poster) | |
| Reinforcement Learning in System Identification (Poster) | |
| SPRINT: Scalable Semantic Policy Pre-training via Language Instruction Relabeling (Poster) | |
| Building a Subspace of Policies for Scalable Continual Learning (Poster) | |
| Graph Inverse Reinforcement Learning from Diverse Videos (Poster) | |
| PnP-Nav: Plug-and-Play Policies for Generalizable Visual Navigation Across Robots (Poster) | |
| Efficient Exploration using Model-Based Quality-Diversity with Gradients (Poster) | |
| Contrastive Value Learning: Implicit Models for Simple Offline RL (Poster) | |
| Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning (Poster) | |
| Toward Effective Deep Reinforcement Learning for 3D Robotic Manipulation: End-to-End Learning from Multimodal Raw Sensory Data (Poster) | |
| Perturbed Quantile Regression for Distributional Reinforcement Learning (Poster) | |
| On All-Action Policy Gradients (Poster) | |
| Locally Constrained Representations in Reinforcement Learning (Poster) | |
| VI2N: A Network for Planning Under Uncertainty based on Value of Information (Poster) | |
| Analyzing the Sensitivity to Policy-Value Decoupling in Deep Reinforcement Learning Generalization (Poster) | |
| Lagrangian Model Based Reinforcement Learning (Poster) | |
| Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes (Poster) | |
| Learning Exploration Policies with View-based Intrinsic Rewards (Poster) | |
| Policy Aware Model Learning via Transition Occupancy Matching (Poster) | |
| Temporary Goals for Exploration (Poster) | |
| Unleashing The Potential of Data Sharing in Ensemble Deep Reinforcement Learning (Poster) | |
| A Framework for Predictable Actor-Critic Control (Poster) | |
| Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments (Poster) | |
| Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning (Poster) | |
| ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning (Poster) | |
| Human-AI Coordination via Human-Regularized Search and Learning (Poster) | |
| In the ZONE: Measuring difficulty and progression in curriculum generation (Poster) | |
| Better state exploration using action sequence equivalence (Poster) | |
| ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation (Poster) | |
| Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization (Poster) | |
| Fine-tuning Offline Policies with Optimistic Action Selection (Poster) | |
| Adversarial Policies Beat Professional-Level Go AIs (Poster) | |
| Offline Reinforcement Learning for Customizable Visual Navigation (Poster) | |
| Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning (Poster) | |
| Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning (Poster) | |
| Investigating Multi-task Pretraining and Generalization in Reinforcement Learning (Poster) | |
| Evaluating Long-Term Memory in 3D Mazes (Poster) | |
| Visual Imitation Learning with Patch Rewards (Poster) | |
| Memory-Efficient Reinforcement Learning with Priority based on Surprise and On-policyness (Poster) | |
| MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning (Poster) | |
| Offline Reinforcement Learning on Real Robot with Realistic Data Sources (Poster) | |
| Hyperbolic Deep Reinforcement Learning (Poster) | |
| Transformer-based World Models Are Happy With 100k Interactions (Poster) | |
| The Benefits of Model-Based Generalization in Reinforcement Learning (Poster) | |
| BLaDE: Robust Exploration via Diffusion Models (Poster) | |
| Learning Semantics-Aware Locomotion Skills from Human Demonstrations (Poster) | |
| Variance Reduction in Off-Policy Deep Reinforcement Learning using Spectral Normalization (Poster) | |
| Prioritizing Samples in Reinforcement Learning with Reducible Loss (Poster) | |
| Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition (Poster) | |
| MOPA: a Minimalist Off-Policy Approach to Safe-RL (Poster) | |
| Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference (Poster) | |
| The Emphatic Approach to Average-Reward Policy Evaluation (Poster) | |
| Curiosity in Hindsight (Poster) | |
| Train Offline, Test Online: A Real Robot Learning Benchmark (Poster) | |
| Ensemble based uncertainty estimation with overlapping alternative predictions (Poster) | |
| Return Augmentation gives Supervised RL Temporal Compositionality (Poster) | |
| Bayesian Q-learning With Imperfect Expert Demonstrations (Poster) | |
| Variance Double-Down: The Small Batch Size Anomaly in Multistep Deep Reinforcement Learning (Poster) | |
| Guiding Exploration Towards Impactful Actions (Poster) | |
| Multi-Agent Policy Transfer via Task Relationship Modeling (Poster) | |
| Foundation Models for History Compression in Reinforcement Learning (Poster) | |
| Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation (Poster) | |
| Training Equilibria in Reinforcement Learning (Poster) | |
| A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games (Poster) | |
| AsymQ: Asymmetric Q-loss to mitigate overestimation bias in off-policy reinforcement learning (Poster) | |
| Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance (Poster) | |
| Novel Policy Seeking with Constrained Optimization (Poster) | |
| Integrating Episodic and Global Bonuses for Efficient Exploration (Poster) | |
| Design Process is a Reinforcement Learning Problem (Poster) | |
| Efficient Deep Reinforcement Learning Requires Regulating Statistical Overfitting (Poster) | |
| Uncertainty-Driven Exploration for Generalization in Reinforcement Learning (Poster) | |
| The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning (Poster) | |
| Understanding Hindsight Goal Relabeling Requires Rethinking Divergence Minimization (Poster) | |
| Implicit Offline Reinforcement Learning via Supervised Learning (Poster) | |
| Domain Invariant Q-Learning for model-free robust continuous control under visual distractions (Poster) | |
| Pre-Training for Robots: Leveraging Diverse Multitask Data via Offline Reinforcement Learning (Poster) | |
| Offline Reinforcement Learning from Heteroskedastic Data Via Support Constraints (Poster) | |
| Imitation from Observation With Bootstrapped Contrastive Learning (Poster) | |
| Improving Assistive Robotics with Deep Reinforcement Learning (Poster) | |
| Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-Oriented Dialogue Systems (Poster) | |
| Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps (Poster) | |
| Efficient Multi-Horizon Learning for Off-Policy Reinforcement Learning (Poster) | |
| Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation (Poster) | |
| CLUTR: Curriculum Learning via Unsupervised Task Representation Learning (Poster) | |
| Revisiting Bellman Errors for Offline Model Selection (Poster) | |
| What Makes Certain Pre-Trained Visual Representations Better for Robotic Learning? (Poster) | |
| Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier (Poster) | |
| Contrastive Example-Based Control (Poster) | |
| Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm (Poster) | |
| Adversarial Cheap Talk (Poster) | |
| Giving Robots a Hand: Broadening Generalization via Hand-Centric Human Video Demonstrations (Poster) | |
| On The Fragility of Learned Reward Functions (Poster) | |
| Model and Method: Training-Time Attack for Cooperative Multi-Agent Reinforcement Learning (Poster) | |
| Planning Immediate Landmarks of Targets for Model-Free Skill Transfer across Agents (Poster) | |
| Confidence-Conditioned Value Functions for Offline Reinforcement Learning (Poster) | |
| A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning (Poster) | |
| Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective (Poster) | |
| Learning Successor Feature Representations to Train Robust Policies for Multi-task Learning (Poster) | |
| Automated Dynamics Curriculums for Deep Reinforcement Learning (Poster) | |
| Deconfounded Imitation Learning (Poster) | |
| Compositional Task Generalization with Modular Successor Feature Approximators (Poster) | |
| Neural All-Pairs Shortest Path for Reinforcement Learning (Poster) | |
| Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction (Poster) | |
| Scaling Covariance Matrix Adaptation MAP-Annealing to High-Dimensional Controllers (Poster) | |
| On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning (Poster) | |
| Emergent collective intelligence from massive-agent cooperation and competition (Poster) | |
| Rethinking Learning Dynamics in RL using Adversarial Networks (Poster) | |
| In-context Reinforcement Learning with Algorithm Distillation (Poster) | |
| SEM2: Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model (Poster) | |
| Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines (Poster) | |
| Imitating Human Behaviour with Diffusion Models (Poster) | |
| Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks (Poster) | |
| A Game-Theoretic Perspective of Generalization in Reinforcement Learning (Poster) | |
| Quantization-aware Policy Distillation (QPD) (Poster) | |
| Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search (Poster) | |
| Cyclophobic Reinforcement Learning (Poster) | |
| Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation (Poster) | |
| VARIATIONAL REPARAMETRIZED POLICY LEARNING WITH DIFFERENTIABLE PHYSICS (Poster) | |
| Efficient Multi-Task Reinforcement Learning via Selective Behavior Sharing (Poster) | |
| A study of natural robustness of deep reinforcement learning algorithms towards adversarial perturbations (Poster) | |
| Multi-skill Mobile Manipulation for Object Rearrangement (Poster) | |
| Learning Representations for Reinforcement Learning with Hierarchical Forward Models (Poster) | |
| Simple Emergent Action Representations from Multi-Task Policy Training (Poster) | |
| Towards True Lossless Sparse Communication in Multi-Agent Systems (Poster) | |
| Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning (Poster) | |
| Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning (Poster) | |
| Choreographer: Learning and Adapting Skills in Imagination (Poster) | |
| Efficient Offline Policy Optimization with a Learned Model (Poster) | |
| Learning a Domain-Agnostic Policy through Adversarial Representation Matching for Cross-Domain Policy Transfer (Poster) | |