Josh Creek 259b2adc07 fix(training): Guard GoalRateCallback against a missing goal_scored key ...

The vendored godot_rl sync bridge (Game/addons/godot_rl_agents/sync.gd,
_training_process) snapshots each agent's info dict once per tick and its
own inline comment already flags that reset-timing path as incomplete
("NEEDS REFACTOR"); at least one agent's terminal-step info can arrive
without "goal_scored" at all. Indexing it directly crashed a training run
(20260729-0607-curric-s1-unmask-retry2) within minutes of starting. Skip
episodes missing the key instead of crashing training over a
monitoring-only metric.

2026-07-29 08:35:20 +01:00

..

checkpoints

chore(training): Add 20260729-0607-curric-s1-unmask-retry2 checkpoints, logs, and exported policy

2026-07-29 06:08:10 +01:00

logs

chore(training): Add 20260729-0607-curric-s1-unmask-retry2 checkpoints, logs, and exported policy

2026-07-29 06:08:10 +01:00

cosmic_env.py

feat(*): Add exported Linux binary training path for faster parallel instances

2026-07-28 20:56:14 +01:00

curriculum_state_gen1.json

feat(*): Start curriculum generation 2, seeded from curric-s5-aggression

2026-07-26 19:00:38 +01:00

curriculum_state.json

chore(training): curriculum progress after 20260729-0607-curric-s1-unmask-retry2

2026-07-29 06:09:25 +01:00

curriculum.py

feat(*): Start curriculum generation 2, seeded from curric-s5-aggression

2026-07-26 19:00:38 +01:00

curriculum.sh

feat(*): add staged curriculum training with an automated stage-by-stage orchestrator

2026-07-21 12:38:51 +01:00

eval_history.json

chore(training): curriculum progress after 20260729-0607-curric-s1-unmask-retry2

2026-07-29 06:09:25 +01:00

evaluate.py

fix(*): apply the locomotion mask during in-game/eval inference, not just training

2026-07-21 22:23:09 +01:00

export_linux.sh

feat(*): Add exported Linux binary training path for faster parallel instances

2026-07-28 20:56:14 +01:00

export_policy.py

feat(*): Add self-play RL training pipeline with PPO trainer, in-game GDScript policy inference, and bot opponent support in Match mode

2026-07-18 19:32:51 +01:00

next_long_run.sh

feat(*): Add long training run script

2026-07-20 07:18:13 +01:00

next_run.sh

feat(training): Add next_run.sh to idempotently kick off the next run resuming from the newest final.zip

2026-07-19 19:16:01 +01:00

requirements.txt

feat(*): Add self-play RL training pipeline with PPO trainer, in-game GDScript policy inference, and bot opponent support in Match mode

2026-07-18 19:32:51 +01:00

run_training.sh

feat(*): Add exported Linux binary training path for faster parallel instances

2026-07-28 20:56:14 +01:00

setup_linux.sh

feat(*): Add exported Linux binary training path for faster parallel instances

2026-07-28 20:56:14 +01:00

start_training.sh

feat(*): Add idempotent tmux-based training scripts for the Linux box

2026-07-19 10:27:21 +01:00

train.py

fix(training): Guard GoalRateCallback against a missing goal_scored key

2026-07-29 08:35:20 +01:00