DeepMind Control Suite

A set of continuous-control RL tasks built on MuJoCo with a standardized interface.

Papers using DeepMind Control Suite (66)

Wasserstein Policy Optimization2025 · 5 citesTask-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization2026Implicit Action Chunking for Smooth Continuous Control2026ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC2026Neural Co-state Policies: Structuring Hidden States in Recurrent Reinforcement Learning2026Revisiting Mixture Policies in Entropy-Regularized Actor-Critic2026Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds2026Mean Flow Policy Optimization2026Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving2026Decoupling Task and Behavior: A Two-Stage Reward Curriculum in Reinforcement Learning for Robotics2026ResWM: Residual-Action World Model for Visual RL2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation2026FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies2026Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning2026Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization2026Reward Learning through Ranking Mean Squared Error2026Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback2026Latent Action World Models for Control with Unlabeled Trajectories2025Spectral Representation-based Reinforcement Learning2025AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning2025Bootstrap Off-policy with World Model2025Test-driven Reinforcement Learning in Continuous Control2025Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning2025Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning2025A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy Optimization2025Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions2025Off-policy Reinforcement Learning with Model-based Exploration Augmentation2025What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?2025One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning2025Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control2025One-Step Flow Policy Mirror Descent2025Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning2025Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions2025Flow-Based Policy for Online Reinforcement Learning2025The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning2025Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning2025MRS: Multi-Resolution Skills for HRL Agents2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning2025Fisher-Guided Selective Forgetting: Mitigating The Primacy Bias in Deep Reinforcement Learning2025Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization2025SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning2024Reward-free World Models for Online Imitation Learning2024UniZero: Generalized and Efficient Planning with Scalable Latent World Models2024Effective Exploration Based on the Structural Information Principles2024 · 3 citesFocus On What Matters: Separated Models For Visual-Based RL Generalization2024 · 2 citesActor-Critic Reinforcement Learning with Phased Actor2024 · 1 citesGeneralizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization2024 · 1 citesStealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning2024 · 1 citesHindsight PRIORs for Reward Learning from Human Preferences2024PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning2024Intrinsic Dynamics-Driven Generalizable Scene Representations for Vision-Oriented Decision-Making Applications2024iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning2024Stabilizing Extreme Q-learning by Maclaurin Expansion2024Decoupling regularization from the action space2024Uncertainty-Aware Reward-Free Exploration with General Function Approximation2024ROER: Regularized Optimal Experience Replay2024ProSpec RL: Plan Ahead, then Execute2024CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning2024State-Novelty Guided Action Persistence in Deep Reinforcement Learning2024Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences2024Bisimulation metric for Model Predictive Control2024Masked Generative Priors Improve World Models Sequence Modelling Capabilities2024Neuroplastic Expansion in Deep Reinforcement Learning2024MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL2024Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions2024Curriculum Reinforcement Learning for Complex Reward Functions2024