Copertina

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nauman, Michal, Bortkiewicz, Michał, Miłoś, Piotr, Trzciński, Tomasz, Ostaszewski, Mateusz, Cygan, Marek
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Case for Validation Buffer in Pessimistic Actor-Critic
di: Nauman, Michal, et al.
Pubblicazione: (2024)

Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control
di: Nauman, Michal, et al.
Pubblicazione: (2024)

On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics
di: Nauman, Michal, et al.
Pubblicazione: (2023)

Reward-Conditioned Reinforcement Learning
di: Nauman, Michal, et al.
Pubblicazione: (2026)

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
di: Wołczyk, Maciej, et al.
Pubblicazione: (2024)

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning
di: Surdej, Rafał, et al.
Pubblicazione: (2025)

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

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
di: Wang, Kevin, et al.
Pubblicazione: (2025)

Contrastive Representations for Temporal Reasoning
di: Ziarko, Alicja, et al.
Pubblicazione: (2025)

When Does Non-Uniform Replay Matter in Reinforcement Learning?
di: Korniak, Michal, et al.
Pubblicazione: (2026)

Learning Continually by Spectral Regularization
di: Lewandowski, Alex, et al.
Pubblicazione: (2024)

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
di: Nauman, Michal, et al.
Pubblicazione: (2025)

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

What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
di: Zawalski, Michał, et al.
Pubblicazione: (2024)

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization
di: Masarczyk, Wojciech, et al.
Pubblicazione: (2025)

MISS: Multiclass Interpretable Scoring Systems
di: Grzeszczyk, Michal K., et al.
Pubblicazione: (2024)

Off-Policy Correction For Multi-Agent Reinforcement Learning
di: Zawalski, Michał, et al.
Pubblicazione: (2021)

Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss
di: Hwang, Ukjo, et al.
Pubblicazione: (2025)

Actor-Critic Reinforcement Learning with Phased Actor
di: Wu, Ruofan, et al.
Pubblicazione: (2024)

Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertainty
di: Özalp, Uğurcan
Pubblicazione: (2026)

What Does Flow Matching Bring To TD Learning?
di: Agrawalla, Bhavya, et al.
Pubblicazione: (2026)

Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
di: Ludziejewski, Jan, et al.
Pubblicazione: (2025)

Amortized Causal Discovery with Prior-Fitted Networks
di: Sypniewski, Mateusz, et al.
Pubblicazione: (2025)

floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL
di: Agrawalla, Bhavya, et al.
Pubblicazione: (2025)

Subgoal Search For Complex Reasoning Tasks
di: Czechowski, Konrad, et al.
Pubblicazione: (2021)

MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts
di: Pióro, Maciej, et al.
Pubblicazione: (2024)

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

A Bitter Lesson for Data Filtering
di: Mohri, Christopher, et al.
Pubblicazione: (2026)

GEPAR3D: Geometry Prior-Assisted Learning for 3D Tooth Segmentation
di: Szczepański, Tomasz, et al.
Pubblicazione: (2025)

Debate2Create: Robot Co-design via Multi-Agent LLM Debate
di: Qiu, Kevin, et al.
Pubblicazione: (2025)

The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning
di: Jayalath, Dulhan, et al.
Pubblicazione: (2024)

Decoupled Relative Learning Rate Schedules
di: Ludziejewski, Jan, et al.
Pubblicazione: (2025)

Feature importance analysis for patient management decisions
di: Valko, Michal, et al.
Pubblicazione: (2026)

Distance metric learning for conditional anomaly detection
di: Valko, Michal, et al.
Pubblicazione: (2026)

PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
di: Chen, Yimeng, et al.
Pubblicazione: (2025)

Learning predictive models for combinations of heterogeneous proteomic data sources
di: Valko, Michal, et al.
Pubblicazione: (2026)

Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
di: Olko, Mateusz, et al.
Pubblicazione: (2025)

Flow Actor-Critic for Offline Reinforcement Learning
di: Chae, Jongseong, et al.
Pubblicazione: (2026)

Solving cold start in news recommendations: a RippleNet-based system for large scale media outlet
di: Radziszewski, Karol, et al.
Pubblicazione: (2025)

ELROND: Exploring and decomposing intrinsic capabilities of diffusion models
di: Skierś, Paweł, et al.
Pubblicazione: (2026)