docs(echo): add TRL backend note for ECHO

[sergiopaniego]

Summary

Adds examples/echo_world_model/backends/trl.md, a design note showing how the ECHO objective maps onto TRL's GRPOTrainer (the framework OpenEnv recommends for RL training), and links it in the example's
backends table. ECHO ships SkyRL/Tinker/Foundry notes but not TRL, the HF-native path, so this closes that gap. Same propositional style as the existing tinker.md and foundry-finetuning.md notes — it documents
the pattern, it is not a shipped implementation.

Type of Change

• Bug fix
• New feature
• Breaking change
• Documentation
• New environment
• Refactoring

Alignment Checklist

Before submitting, verify:

• I have read .claude/docs/PRINCIPLES.md and this PR aligns with our principles
• I have checked .claude/docs/INVARIANTS.md and no invariants are violated
• I have run /pre-submit-pr (or bash .claude/hooks/lint.sh and tests) and addressed all issues — docs-only, no code paths touched

RFC Status

• Not required (bug fix, docs, minor refactoring)
• RFC exists: feat: ECHO env-token world modeling (RFC 010 + two runnable examples) #819
• RFC needed (will create before merge)

Test Plan

Markdown-only: new backends/trl.md + one line in the README backends table. The note is consistent with echo_loss.py and the mask mapping in the sibling backend docs. The example's existing unit tests still
pass unchanged (6 passed, verified with pytest test_echo.py). The note is explicitly framed as a proposed pattern (following TRL PR #6003), not a runnable adapter.

Claude Code Review

[bot-ci-comment]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.