Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on Darkroom2 5x5 grid ε=0.4
Loading...
242.2
Avg Reward (AT-DPT Attacker)
AT-DPT
196.336
208.243
220.15
232.057
Jun 7, 2025
Avg Reward (AT-DPT Attacker)
Avg Reward (DPT Attacker)
Avg Reward (NPG Attacker)
Avg Reward (Q-learning Attacker)
Avg Reward (Uniform Rand. Attack)
Avg Reward (Clean Env.)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg Reward (AT-DPT Attacker)
Avg Reward (DPT Attacker)
Avg Reward (NPG Attacker)
Avg Reward (Q-learning Attacker)
Avg Reward (Uniform Rand. Attack)
Avg Reward (Clean Env.)
AT-DPT
2025.06
242.2
267.5
241.7
239.1
258.2
267.4
NPG
Pre-evaluation Learnin...
2025.06
237.2
243.7
228.9
228.1
235.3
241.7
AT-DPT
Training Data Subset P...
2025.06
225.2
245.5
226.1
222.7
241.3
250.2
DPT
2025.06
216.1
143.5
202.6
205.9
266.2
306.8
Q-learning
Pre-evaluation Learnin...
2025.06
198.1
238.6
215.4
224.7
229
225.6
Feedback
Search any
task
Search any
task