name: negotiation-env
version: "1.0.0"
description: >
  Strategic Negotiation Simulation Environment where an AI agent learns
  to negotiate under uncertainty with different opponent personalities.
  The agent must maximize profit through multi-round price negotiation
  while adapting to greedy, fair, or impatient opponents.

author: Team MEta_ai
license: Apache-2.0

environment:
  type: simulation
  domain: negotiation
  real_world_task: automated marketplace pricing and negotiation

observation_space:
  type: object
  fields:
    current_offer:
      type: integer
      description: Current price on the table
      range: [100, 1000]
    round:
      type: integer
      description: Current round number
      range: [0, 20]
    max_rounds:
      type: integer
      description: Maximum allowed rounds
    role:
      type: string
      enum: ["buyer", "seller"]
      description: Agent's role in the negotiation
    last_opponent_action:
      type: string
      enum: ["START", "OFFER", "ACCEPT"]
      description: Opponent's last action
    last_opponent_offer:
      type: integer
      description: Opponent's last offered price
      range: [100, 1000]
    history:
      type: array
      description: History of all actions this episode

action_space:
  type: object
  fields:
    action_type:
      type: string
      enum: ["OFFER", "ACCEPT", "REJECT"]
      description: Type of negotiation action
    price:
      type: integer
      description: Price for OFFER actions (ignored for ACCEPT/REJECT)
      range: [100, 1000]

reward:
  type: float
  range: [-50.0, 855.0]
  description: >
    Reward based on deal profit scaled by time factor.
    Partial progress signals during intermediate steps.
    Penalty for failed negotiations (-50), bad deals (-20), 
    and aggressive offers (cumulative -2 per aggressive step).

tasks:
  - name: task_a_easy
    difficulty: easy
    description: Fair opponent, wide ZOPA, 20 rounds
    success_threshold: 0.2

  - name: task_b_medium
    difficulty: medium
    description: Greedy opponent, narrow ZOPA, 15 rounds
    success_threshold: 0.3

  - name: task_c_hard
    difficulty: hard
    description: Impatient opponent, tight margins, 6 rounds
    success_threshold: 0.4

inference:
  script: inference.py
  env_vars:
    - API_BASE_URL
    - MODEL_NAME
    - HF_TOKEN

deployment:
  dockerfile: Dockerfile
  platform: huggingface-spaces
  tag: openenv