meta-rl-dsa-solver / openenv.yaml
s-shah4
Add V1 env
4433dc8
spec_version: 1
name: adapt_dsa_tutor
type: space
runtime: fastapi
app: server.app:app
port: 7860
description: "ADAPT: an adversarial DSA tutor environment for RLVR code generation with hidden tests, tiered problems, and anti-hacking reward signals."
version: "0.2.0"
observation_space:
type: dict
description: "Problem prompt, examples, visible tests, difficulty metadata, reward, pass rates, execution status, and feedback."
action_space:
type: dict
description: "AdaptAction with a Python code string submitted for stdin/stdout evaluation."
reward_range: [0.0, 1.0]
tasks:
- name: easy_double
description: "Easy arithmetic stdin/stdout problem."
difficulty: easy
- name: easy_sum_two
description: "Easy two-integer arithmetic problem."
difficulty: easy
- name: medium_maximum
description: "Medium array scanning problem."
difficulty: medium
- name: medium_count_even
description: "Medium counting problem over a list."
difficulty: medium
- name: hard_reverse_words
description: "Harder string normalization and ordering problem."
difficulty: hard