Picture for Alexander Nikulin

Alexander Nikulin

N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs

Add code
Nov 04, 2024
Viaarxiv icon

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

Add code
Jun 13, 2024
Figure 1 for XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Figure 2 for XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Figure 3 for XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Figure 4 for XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Viaarxiv icon

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Add code
Feb 05, 2024
Figure 1 for Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Figure 2 for Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Figure 3 for Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Figure 4 for Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning
Viaarxiv icon

In-Context Reinforcement Learning for Variable Action Spaces

Add code
Dec 20, 2023
Figure 1 for In-Context Reinforcement Learning for Variable Action Spaces
Figure 2 for In-Context Reinforcement Learning for Variable Action Spaces
Viaarxiv icon

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

Add code
Dec 19, 2023
Viaarxiv icon

Emergence of In-Context Reinforcement Learning from Noise Distillation

Add code
Dec 19, 2023
Viaarxiv icon

Katakomba: Tools and Benchmarks for Data-Driven NetHack

Add code
Jun 14, 2023
Viaarxiv icon

Revisiting the Minimalist Approach to Offline Reinforcement Learning

Add code
May 16, 2023
Viaarxiv icon

Anti-Exploration by Random Network Distillation

Add code
Jan 31, 2023
Viaarxiv icon

Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size

Add code
Nov 20, 2022
Viaarxiv icon