Cover Image

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Kevin, Javali, Ishaan, Bortkiewicz, Michał, Trzciński, Tomasz, Eysenbach, Benjamin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Accelerating Goal-Conditioned RL Algorithms and Research
by: Bortkiewicz, Michał, et al.
Published: (2024)

Is Temporal Difference Learning the Gold Standard for Stitching in RL?
by: Bortkiewicz, Michał, et al.
Published: (2025)

Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
by: Nimonkar, Chirayu, et al.
Published: (2025)

OGBench: Benchmarking Offline Goal-Conditioned RL
by: Park, Seohong, et al.
Published: (2024)

Contrastive Representations for Temporal Reasoning
by: Ziarko, Alicja, et al.
Published: (2025)

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
by: Zheng, Chongyi, et al.
Published: (2023)

HIQL: Offline Goal-Conditioned RL with Latent States as Actions
by: Park, Seohong, et al.
Published: (2023)

A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals
by: Liu, Grace, et al.
Published: (2024)

Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
by: Modirshanechi, Alireza, et al.
Published: (2026)

Horizon Reduction Makes RL Scalable
by: Park, Seohong, et al.
Published: (2025)

Bridging State and History Representations: Understanding Self-Predictive RL
by: Ni, Tianwei, et al.
Published: (2024)

Can We Really Learn One Representation to Optimize All Rewards?
by: Zheng, Chongyi, et al.
Published: (2026)

Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning
by: Zheng, Chongyi, et al.
Published: (2024)

On the Role of Iterative Computation in Reinforcement Learning
by: Ghugare, Raj, et al.
Published: (2026)

Normalizing Flows are Capable Models for RL
by: Ghugare, Raj, et al.
Published: (2025)

Learning to Reach Goals via Diffusion
by: Jain, Vineet, et al.
Published: (2023)

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
by: Myers, Vivek, et al.
Published: (2024)

Efficient LLM Moderation with Multi-Layer Latent Prototypes
by: Chrabąszcz, Maciej, et al.
Published: (2025)

Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
by: Zheng, Haizhong, et al.
Published: (2025)

Horizon Generalization in Reinforcement Learning
by: Myers, Vivek, et al.
Published: (2025)

Contrastive Difference Predictive Coding
by: Zheng, Chongyi, et al.
Published: (2023)

Deep Neighbor Layer Aggregation for Lightweight Self-Supervised Monocular Depth Estimation
by: Boya, Wang, et al.
Published: (2023)

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
by: Nauman, Michal, et al.
Published: (2024)

NiceWebRL: a Python library for human subject experiments with reinforcement learning environments
by: Carvalho, Wilka, et al.
Published: (2025)

Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
by: Pawlak, Stanisław, et al.
Published: (2025)

First-Order Representation Languages for Goal-Conditioned RL
by: Ståhlberg, Simon, et al.
Published: (2025)

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
by: Zeng, Yirong, et al.
Published: (2026)

MagMax: Leveraging Model Merging for Seamless Continual Learning
by: Marczak, Daniel, et al.
Published: (2024)

AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation
by: Sójka, Damian, et al.
Published: (2023)

Exploring the Stability Gap in Continual Learning: The Role of the Classification Head
by: Łapacz, Wojciech, et al.
Published: (2024)

Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
by: Fan, Zhiyuan, et al.
Published: (2026)

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
by: Jeon, Sangwoo, et al.
Published: (2025)

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination
by: Wang, Liangzhou, et al.
Published: (2024)

A Rate-Distortion View of Uncertainty Quantification
by: Apostolopoulou, Ifigeneia, et al.
Published: (2024)

Intention-Conditioned Flow Occupancy Models
by: Zheng, Chongyi, et al.
Published: (2025)

Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards
by: Mohamed, Faisal, et al.
Published: (2026)

Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL
by: Choi, Jinwoo, et al.
Published: (2026)

Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
by: Menon, Achyutha, et al.
Published: (2026)

Masked Self-Supervised Pre-Training for Text Recognition Transformers on Large-Scale Datasets
by: Kišš, Martin, et al.
Published: (2025)

Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
by: Zhou, Yizhi, et al.
Published: (2025)