AI & ML
D'BEAST: Logged Bad Experiences as Explanation for Autonomous Driving Agents
arXiv cs.RO0 views
arXiv:2611.20019v1 Announce Type: cross Abstract: Reinforcement learning agents learn from mistakes, yet their decisions can be difficult to trace back to those experiences. We investigate whether a tabular agent's decisions can be explained by its bad experiences, defined as the training transitions associated with safety or task events. A fixed training log is replayed from the same initial Q-table under three conditions. FULL retains all updates, SKIP omits bad-experience updates, and NEUTRALIZE retains those updates without their event penalties. We illustrate the method on six classic Markov decision processes and evaluate it in closed-loop driving in CARLA. On the full driving task, FULL reached the goal from 33 of 40 test starts, whereas SKIP and NEUTRALIZE reached it from none, indicating that the bad experiences carry decision-relevant information. At the local level, for 47 decisions shortly before a failure of SKIP or NEUTRALIZE, removing or neutralizing a small group of bad experiences, with a median size of one, caused the trained agent to select the failing policy's action in 46 cases. For this agent, the results indicate that its decisions can be explained by its bad experiences.
Source:https://arxiv.org/abs/2611.20019PreviousReactBench-AD: Do Driving VLAs and World-Action Models React to Imminent Hazards in Their Path?NextA Geometric Observer for Visual-Inertial Odometry using Optical-Flow Constraints
Related posts

Elon Musk tries to explain what’s going on with Ukraine and Starlink
0The Verge

Gemini 4 Neon ออก API แล้ว ราคาถูกกว่า Opus 5.5 ถึง 25% คุ้มไหม
0dev.to
🎮 RIFTFIRE Is Now "Null Point" — Live on Playgama
0dev.to
GPT-6.2 Astra vs. Sol: Benchmarks and API Pricing
0dev.to
Building Smarter Manufacturing Systems: How AI, IoT, and Physical AI Work Together
0dev.to
Scale the Model, Scale the Harness: Unlocking a 2 Leap in Mathematical Reasoning
0dev.to