Gautham Vasan
4 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🐝 Cross-Pollinator (14)
🐣
Hot Topic Early Bird
Conferences
CORL (1)
ICML (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
continuous control
(2)
policy gradient
(2)
sample efficiency
(1)
online learning
(1)
robotic manipulation
(1)
incremental learning
(1)
discount factor
(1)
variance reduction
(1)
stochastic process
(1)
action value
(1)
incremental deep policy gradient
(1)
replay buffer
(1)
robotic manipulator
(1)
mobile robot
(1)
batch policy gradient
(1)
on-policy learning
(1)
autoregressive policy
(1)
robotic hardware
(1)
real-world robotics
(1)
hyperparameter sensitivity
(1)
Papers
Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
NIPS 2024
Correcting discount-factor mismatch in on-policy policy gradient methods
ICML 2023
Autoregressive Policies for Continuous Control Deep Reinforcement Learning
IJCAI 2019
Benchmarking Reinforcement Learning Algorithms on Real-World Robots
CORL 2018