#

reward-function

Here are 5 public repositories matching this topic...

DeepGym / deepgym

RL training environments with verifiable rewards for coding agents. Works with TRL, Unsloth, verl, OpenRLHF.

python machine-learning reinforcement-learning deep-learning sandbox evaluation rl code-execution ai-agents daytona llm unsloth coding-agents grpo verifiable-rewards openrlhf reward-function grpo-training

Updated Apr 24, 2026
Python

reveurmichael / space_mining

SpaceMining: a novel RL environment beyond LLM priors

reinforcement-learning-agent reinforcement-learning-environments large-language-models stablebaselines3 llm-evaluation gymnasium-environment reward-function

Updated Sep 2, 2025
Python

henry2-9 / AWS-DeepRacer

Reinforcement learning strategies for AWS DeepRacer — from stable baseline to sub-9 second laps on the re:Invent 2018 track.

machine-learning reinforcement-learning deep-learning autonomous-driving aws-deepracer reward-function deepracer-training

Updated Jun 16, 2025

prabhu-gopal / bohrin

Check the checker: an open standard for testing the graders of RL environments, with proof before every accusation.

python reinforcement-learning mutation-testing evaluation benchmarks grader ai-safety verifier rl-environments ai-evaluation evals llm-evaluation coding-agents rlvr reward-function reward-hacking

Updated Sep 29, 2026
Python

scscodes / deepracer

AWS Deep Racer workflow: reward functions, log analysis, and references for model tuning.

aws reinforcement-learning deepracer reward-function

Updated Sep 24, 2024
Python

Add this topic to your repo

To associate your repository with the reward-function topic, visit your repo's landing page and select "manage topics."