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 multiagent 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.
| Invited talk: PierreYves Oudeyer "Machines that invent their own problems: Towards open-ended learning of skills" (Talk) | |
| Contributed Talk: Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planning (Talk) | |
| Contributed Talk: Maximum Reward Formulation In Reinforcement Learning (Talk) | |
| Contributed Talk: Accelerating Reinforcement Learning with Learned Skill Priors (Talk) | |
| Contributed Talk: Asymmetric self-play for automatic goal discovery in robotic manipulation (Talk) | |
| Invited talk: Marc Bellemare "Autonomous navigation of stratospheric balloons using reinforcement learning" (Talk) | |
| Break | |
| Invited talk: Peter Stone "Grounded Simulation Learning for Sim2Real with Connections to Off-Policy Reinforcement Learning" (Talk) | |
| Contributed Talk: Mirror Descent Policy Optimization (Talk) | |
| Contributed Talk: Planning from Pixels using Inverse Dynamics Models (Talk) | |
| Invited talk: Matt Botvinick "Alchemy: A Benchmark Task Distribution for Meta-Reinforcement Learning Research" (Talk) | |
| Poster session 1 (Poster session) | |
| Invited talk: Susan Murphy "We used RL but…. Did it work?!" (Talk) | |
| Contributed Talk: MaxEnt RL and Robust Control (Talk) | |
| Contributed Talk: Reset-Free Lifelong Learning with Skill-Space Planning (Talk) | |
| Invited talk: Anusha Nagabandi "Model-based Deep Reinforcement Learning for Robotic Systems" (Talk) | |
| Break | |
| Invited talk: Ashley Edwards "Learning Offline from Observation" (Talk) | |
| NeurIPS RL Competitions: Flatland challenge (Talk) | |
| NeurIPS RL Competitions: Learning to run a power network (Talk) | |
| NeurIPS RL Competitions: Procgen challenge (Talk) | |
| NeurIPS RL Competitions: MineRL (Talk) | |
| Invited talk: Karen Liu "Deep Reinforcement Learning for Physical Human-Robot Interaction" (Talk) | |
| Panel discussion | |
| Poster session 2 (Poster session) | |
| Poster: Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research (Poster) | |
| Poster: Reinforcement Learning with Latent Flow (Poster) | |
| Poster: Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization (Poster) | |
| Poster: AWAC: Accelerating Online Reinforcement Learning With Offline Datasets (Poster) | |
| Poster: Inter-Level Cooperation in Hierarchical Reinforcement Learning (Poster) | |
| Poster: Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning (Poster) | |
| Poster: Measuring Visual Generalization in Continuous Control from Pixels (Poster) | |
| Poster: Policy Learning Using Weak Supervision (Poster) | |
| Poster: Unsupervised Domain Adaptation for Visual Navigation (Poster) | |
| Poster: Learning Markov State Abstractions for Deep Reinforcement Learning (Poster) | |
| Poster: Value Generalization among Policies: Improving Value Function with Policy Representation (Poster) | |
| Poster: Backtesting Optimal Trade Execution Policies in Agent-Based Market Simulator (Poster) | |
| Poster: Successor Landmarks for Efficient Exploration and Long-Horizon Navigation (Poster) | |
| Poster: Multi-task Reinforcement Learning with a Planning Quasi-Metric (Poster) | |
| Poster: R-LAtte: Visual Control via Deep Reinforcement Learning with Attention Network (Poster) | |
| Poster: Quantifying Differences in Reward Functions (Poster) | |
| Poster: DERAIL: Diagnostic Environments for Reward And Imitation Learning (Poster) | |
| Poster: Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations (Poster) | |
| Poster: Unlocking the Potential of Deep Counterfactual Value Networks (Poster) | |
| Poster: FactoredRL: Leveraging Factored Graphs for Deep Reinforcement Learning (Poster) | |
| Poster: Reusability and Transferability of Macro Actions for Reinforcement Learning (Poster) | |
| Poster: Interactive Visualization for Debugging RL (Poster) | |
| Poster: A Deep Value-based Policy Search Approach for Real-world Vehicle Repositioning on Mobility-on-Demand Platforms (Poster) | |
| Poster: FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance (Poster) | |
| Poster: Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks (Poster) | |
| Poster: Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning (Poster) | |
| Poster: XLVIN: eXecuted Latent Value Iteration Nets (Poster) | |
| Poster: Beyond Exponentially Discounted Sum: Automatic Learning of Return Function (Poster) | |
| Poster: XT2: Training an X-to-Text Typing Interface with Online Learning from Implicit Feedback (Poster) | |
| Poster: Greedy Multi-Step Off-Policy Reinforcement Learning (Poster) | |
| Poster: Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning (Poster) | |
| Poster: Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation (Poster) | |
| Poster: ReaPER: Improving Sample Efficiency in Model-Based Latent Imagination (Poster) | |
| Poster: Model-Based Reinforcement Learning: A Compressed Survey (Poster) | |
| Poster: BeBold: Exploration Beyond the Boundary of Explored Regions (Poster) | |
| Poster: Model-Based Visual Planning with Self-Supervised Functional Distances (Poster) | |
| Poster: Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning (Poster) | |
| Poster: Utilizing Skipped Frames in Action Repeats via Pseudo-Actions (Poster) | |
| Poster: Continual Model-Based Reinforcement Learning withHypernetworks (Poster) | |
| Poster: Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies (Poster) | |
| Poster: Policy Guided Planning in Learned Latent Space (Poster) | |
| Poster: Planning from Pixels using Inverse Dynamics Models (Poster) | |
| Poster: Maximum Reward Formulation In Reinforcement Learning (Poster) | |
| Poster: Reset-Free Lifelong Learning with Skill-Space Planning (Poster) | |
| Poster: Mirror Descent Policy Optimization (Poster) | |
| Poster: MaxEnt RL and Robust Control (Poster) | |
| Poster: Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planning (Poster) | |
| Poster: Provably Efficient Policy Optimization via Thompson Sampling (Poster) | |
| Poster: Weighted Bellman Backups for Improved Signal-to-Noise in Q-Updates (Poster) | |
| Poster: Efficient Competitive Self-Play Policy Optimization (Poster) | |
| Poster: Asymmetric self-play for automatic goal discovery in robotic manipulation (Poster) | |
| Poster: Correcting Momentum in Temporal Difference Learning (Poster) | |
| Poster: Decoupling Exploration and Exploitation in Meta-Reinforcement Learning without Sacrifices (Poster) | |
| Poster: Diverse Exploration via InfoMax Options (Poster) | |
| Poster: Parrot: Data-driven Behavioral Priors for Reinforcement Learning (Poster) | |
| Poster: C-Learning: Horizon-Aware Cumulative Accessibility Estimation (Poster) | |
| Poster: Accelerating Reinforcement Learning with Learned Skill Priors (Poster) | |
| Poster: C-Learning: Learning to Achieve Goals via Recursive Classification (Poster) | |
| Poster: Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers (Poster) | |
| Poster: Learning to Reach Goals via Iterated Supervised Learning (Poster) | |
| Poster: Unified View of Inference-based Off-policy RL: Decoupling Algorithmic and Implemental Source of Performance Gaps (Poster) | |
| Poster: Learning to Sample with Local and Global Contexts in Experience Replay Buffer (Poster) | |
| Poster: Adversarial Environment Generation for Learning to Navigate the Web (Poster) | |
| Poster: Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in First-person Simulated 3D Environments (Poster) | |
| Poster: DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies (Poster) | |
| Poster: Discovery of Options via Meta-Gradients (Poster) | |
| Poster: GRAC: Self-Guided and Self-Regularized Actor-Critic (Poster) | |
| Poster: Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity (Poster) | |
| Poster: Deep Bayesian Quadrature Policy Gradient (Poster) | |
| Poster: PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards (Poster) | |
| Poster: A Policy Gradient Method for Task-Agnostic Exploration (Poster) | |
| Poster: Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning (Poster) | |
| Poster: Skill Transfer via Partially Amortized Hierarchical Planning (Poster) | |
| Poster: On Effective Parallelization of Monte Carlo Tree Search (Poster) | |
| Poster: Average Reward Reinforcement Learning with Monotonic Policy Improvement (Poster) | |
| Poster: Combating False Negatives in Adversarial Imitation Learning (Poster) | |
| Poster: Evaluating Agents Without Rewards (Poster) | |
| Poster: Learning Latent Landmarks for Generalizable Planning (Poster) | |
| Poster: Conservative Safety Critics for Exploration (Poster) | |
| Poster: Solving Compositional Reinforcement Learning Problems via Task Reduction (Poster) | |
| Poster: Deep Q-Learning with Low Switching Cost (Poster) | |
| Poster: Learning to Represent Action Values as a Hypergraph on the Action Vertices (Poster) | |
| Poster: Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets (Poster) | |
| Poster: TACTO: A Simulator for Learning Control from Touch Sensing (Poster) | |
| Poster: Safe Reinforcement Learning with Natural Language Constraints (Poster) | |
| Poster: Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks (Poster) | |
| Poster: An Examination of Preference-based Reinforcement Learning for Treatment Recommendation (Poster) | |
| Poster: Model-based Navigation in Environments with Novel Layouts Using Abstract $n$-D Maps (Poster) | |
| Poster: Online Safety Assurance for Deep Reinforcement Learning (Poster) | |
| Poster: Lyapunov Barrier Policy Optimization (Poster) | |
| Poster: Evolving Reinforcement Learning Algorithms (Poster) | |
| Poster: Chaining Behaviors from Data with Model-Free Reinforcement Learning (Poster) | |
| Poster: Pairwise Weights for Temporal Credit Assignment (Poster) | |
| Poster: Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning (Poster) | |
| Poster: Understanding Learned Reward Functions (Poster) | |
| Poster: Reinforcement Learning with Bayesian Classifiers: Efficient Skill Learning from Outcome Examples (Poster) | |
| Poster: Model-Based Reinforcement Learning via Latent-Space Collocation (Poster) | |
| Poster: A Variational Inference Perspective on Goal-Directed Behavior in Reinforcement Learning (Poster) | |
| Poster: SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II (Poster) | |
| Poster: Latent State Models for Meta-Reinforcement Learning from Images (Poster) | |
| Poster: Dream and Search to Control: Latent Space Planning for Continuous Control (Poster) | |
| Poster: Explanation Augmented Feedback in Human-in-the-Loop Reinforcement Learning (Poster) | |
| Poster: Goal-Conditioned Reinforcement Learning in the Presence of an Adversary (Poster) | |
| Poster: Domain Adversarial Reinforcement Learning (Poster) | |
| Poster: Safety Aware Reinforcement Learning (Poster) | |
| Poster: Sample Efficient Training in Multi-Agent AdversarialGames with Limited Teammate Communication (Poster) | |
| Poster: Amortized Variational Deep Q Network (Poster) | |
| Poster: Unsupervised Task Clustering for Multi-Task Reinforcement Learning (Poster) | |
| Poster: Learning Intrinsic Symbolic Rewards in Reinforcement Learning (Poster) | |
| Poster: Action and Perception as Divergence Minimization (Poster) | |
| Poster: Randomized Ensembled Double Q-Learning: Learning Fast Without a Model (Poster) | |
| Poster: Compute- and Memory-Efficient Reinforcement Learning with Latent Experience Replay (Poster) | |
| Poster: Emergent Road Rules In Multi-Agent Driving Environments (Poster) | |
| Poster: Mastering Atari with Discrete World Models (Poster) | |
| Poster: Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads (Poster) | |
| Poster: Decoupling Representation Learning from Reinforcement Learning (Poster) | |
| Poster: Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning (Poster) | |
| Poster: Preventing Value Function Collapse in Ensemble Q-Learning by Maximizing Representation Diversity (Poster) | |
| Poster: Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments (Poster) | |
| Poster: Bringing order into Actor-Critic Algorithms usingStackelberg Games (Poster) | |
| Poster: Disentangled Planning and Control in Vision Based Robotics via Reward Machines (Poster) | |
| Poster: Maximum Mutation Reinforcement Learning for Scalable Control (Poster) | |
| Poster: What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study (Poster) | |
| Poster: Hyperparameter Auto-tuning in Self-Supervised Robotic Learning (Poster) | |
| Poster: An Algorithmic Causal Model of Credit Assignment in Reinforcement Learning (Poster) | |
| Poster: Multi-Agent Option Critic Architecture (Poster) | |
| Poster: Modular Training, Integrated Planning Deep Reinforcement Learning for Mobile Robot Navigation (Poster) | |
| Poster: Semantic State Representation for Reinforcement Learning (Poster) | |
| Poster: Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning (Poster) | |
| Poster: Regularized Inverse Reinforcement Learning (Poster) | |
| Poster: Energy-based Surprise Minimization for Multi-Agent Value Factorization (Poster) | |
| Poster: Addressing reward bias in Adversarial Imitation Learning with neutral reward functions (Poster) | |
| Poster: DREAM: Deep Regret minimization with Advantage baselines and Model-free learning (Poster) | |
| Poster: OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning (Poster) | |
| Poster: Data-Efficient Reinforcement Learning with Self-Predictive Representations (Poster) | |
| Poster: PettingZoo: Gym for Multi-Agent Reinforcement Learning (Poster) | |
| Poster: D2RL: Deep Dense Architectures in Reinforcement Learning (Poster) | |
| Poster: Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms (Poster) | |
| Poster: Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (Poster) | |
| Poster: Targeted Query-based Action-Space Adversarial Policies on Deep Reinforcement Learning Agents (Poster) | |
| Poster: Abstract Value Iteration for Hierarchical Deep Reinforcement Learning (Poster) | |
| Poster: Learning to Weight Imperfect Demonstrations (Poster) | |
| Poster: Structure and randomness in planning and reinforcement learning (Poster) | |
| Poster: Parameter-based Value Functions (Poster) | |
| Poster: Influence-aware Memory for Deep Reinforcement Learning in POMDPs (Poster) | |
| Poster: How to make Deep RL work in Practice (Poster) | |
| Poster: Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning (Poster) | |
| Poster: Which Mutual-Information Representation Learning Objectives are Sufficient for Control? (Poster) | |
| Poster: Curriculum Learning through Distilled Discriminators (Poster) | |
| Poster: Self-Supervised Policy Adaptation during Deployment (Poster) | |
| Poster: Trust, but verify: model-based exploration in sparse reward environments (Poster) | |
| Poster: Optimizing Traffic Bottleneck Throughput using Cooperative, Decentralized Autonomous Vehicles (Poster) | |
| Poster: Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking (Poster) | |
Successful Page Load