Tag feed

#reinforcement-learning

238 posts54 followers

Explore Hashnode

Alternatives

Trending tags this week

JSJeevika Slocal-minima.hashnode.dev2d ago · 10 min read

Building an RL Traffic Agent for Indian Roads, Part 8: The Ramp That Wouldn't Go Away

Part 7 ended on a table that looked clean. Nav scaling fixed the steering lock-in, extending training to 100,000 steps gave the CNN room to actually learn road geometry, and every metric in that closi

0

JSJeevika Slocal-minima.hashnode.dev2d ago · 7 min read

Building an RL Traffic Agent for Indian Roads, Part 7: Unlocked, and Immediately Falling Apart Differently

The critic had curvature. The actor finally had somewhere to go. Which meant, for the first time, the car actually moved. It also meant a new set of problems, because "moving" and "driving well" turne

0

JSJeevika Slocal-minima.hashnode.dev2d ago · 13 min read

Building an RL Traffic Agent for Indian Roads, Part 6: The Frozen Robot

Everything in Part 5 worked. The pipeline ran end to end, LIDAR in, occupancy grid out, latent vector through the actor, continuous steering and throttle out the other side. Then I actually let it tra

0

JSJeevika Slocal-minima.hashnode.dev2d ago · 18 min read

Building an RL Traffic Agent for Indian Roads, Part 5: The Math, the Bugs, and Everything That Broke

Part 4 was the reasoning that got me to an architecture on paper. This part is what happened once I actually tried to build it, which turned out to be a very different exercise. Most of Part 4 was "wh

0

JSJeevika Slocal-minima.hashnode.dev2d ago · 19 min read

Building an RL Traffic Agent for Indian Roads, Part 4: The Architecture

After going through the theory, I didn't want to just jump into code. I wanted a base to build on first, a shape for the whole thing before I touched a single line of Python. So the first question I h

0

JSJeevika Slocal-minima.hashnode.dev2d ago · 8 min read

Self Driving Cars, Part 3: Building a 2D Simulator to Understand RL

After going through the self-driving landscape, Tesla, Waymo, BYD, and the rest, covered in the first two parts of this series, I spent a couple of weeks studying the architecture and approach compani

0

JSJeevika Slocal-minima.hashnode.dev3d ago · 8 min read

Self Driving Cars, Part 2: It's Not Just Tesla vs Waymo

Part 1 was Tesla vs Waymo, and by the end of it I'd landed on Tesla, mostly because of how the two scale. But somewhere in my own head after publishing that, I realised I'd boxed myself into a pretty

0

CMChaeyeon Mia Leemiainflorence.hashnode.devAug 3 · 9 min read

Why GRPO, Dr. GRPO, and DAPO Are All the Same Algorithm in Disguise: The Group-Standard-Deviation Identity

You've spent hours tuning your RLVR training run. GRPO converges too aggressively on hard problems. You switch to Dr. GRPO for stability, but then you read that DAPO gets better results by throwing aw

0

YSYusuf Solomonysolomon.hashnode.devAug 1 · 18 min read

Implementing Algorithms for the Multi-Armed-Bandit Problem

Let's suppose you are faced with a dilemma; there are k possible actions to take, and you have only T opportunities to take actions. Taking an action returns a reward R from an underlying reward distr

0

MMikuzmikuz.hashnode.devJul 31 · 8 min read

A Practical Guide to Reinforcement Learning Evaluation

Reinforcement learning has emerged as the preferred method for the final phase of large language model post-training, with systems like DeepSeek-R1 and OpenAI's o-series demonstrating capabilities bey

0

#reinforcement-learning

Search Hashnode

#reinforcement-learning

Explore Hashnode

Trending tags this week

Building an RL Traffic Agent for Indian Roads, Part 8: The Ramp That Wouldn't Go Away

Building an RL Traffic Agent for Indian Roads, Part 7: Unlocked, and Immediately Falling Apart Differently

Building an RL Traffic Agent for Indian Roads, Part 6: The Frozen Robot

Building an RL Traffic Agent for Indian Roads, Part 5: The Math, the Bugs, and Everything That Broke

Building an RL Traffic Agent for Indian Roads, Part 4: The Architecture

Self Driving Cars, Part 3: Building a 2D Simulator to Understand RL

Self Driving Cars, Part 2: It's Not Just Tesla vs Waymo

Why GRPO, Dr. GRPO, and DAPO Are All the Same Algorithm in Disguise: The Group-Standard-Deviation Identity

Implementing Algorithms for the Multi-Armed-Bandit Problem

A Practical Guide to Reinforcement Learning Evaluation