Piotr Stańczyk
6 papers · 2020–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (16)
👥
Mega-Team · Squad
❓
The Questioner
Top co-authors
Research topics
Machine Learning
(5)
Reinforcement Learning
(4)
Methods
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Application Areas
(3)
Core AI
(3)
Natural Language Processing
(2)
Applications · Reinforcement Learning
(2)
Applications · Natural Language Processing
(1)
Architectures
(1)
Generation
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Keywords
reinforcement learning
(3)
policy gradient
(2)
reinforcement learning from human feedback
(2)
knowledge distillation
(2)
deep rl
(2)
language model
(1)
game ai
(1)
game environment
(1)
on-policy learning
(1)
actor-critic method
(1)
best-of-n sampling
(1)
textual entailment
(1)
reference-free evaluation
(1)
abstractive summarization
(1)
factual consistency
(1)
distribution mismatch
(1)
large language model
(1)
reinforcement learning environment
(1)
multi-agent system
(1)
game simulation
(1)
Papers
BOND: Aligning LLMs with Best-of-N Distillation
ICLR 2025
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
ICLR 2024
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
ACL 2023
What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study
ICLR 2021
Google Research Football: A Novel Reinforcement Learning Environment
AAAI 2020
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference
ICLR 2020