Piotr Stańczyk
6 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (3) 🏃 Academic Marathon (5) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🌈
Renaissance Researcher
(5)
🌉
Interdisciplinary Bridge
👥
Mega-Team
(20)
❓
The Questioner
Conferences
ICLR (4)
AAAI (1)
ACL (1)
Top co-authors
Keywords
reinforcement learning
(2)
policy gradient
(1)
game ai
(1)
game environment
(1)
deep rl
(1)
textual entailment
(1)
reference-free evaluation
(1)
abstractive summarization
(1)
factual consistency
(1)
reinforcement learning environment
(1)
multi-agent system
(1)
game simulation
(1)
3d physics simulation
(1)
multi-agent experiment
(1)
football benchmark
(1)
reference-free reward
(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