donkeycar-rl-autoresearch/agent/experiments/exp18_parallel_450k_v2.py

"""
Exp 18: Parallel DummyVecEnv — 450k steps, fixed efficiency gate (v2).

Problem with Exp 17: circular exploit dominated entire run.
Root cause: v6 efficiency gate window=30 steps (~1.4s at 22fps).
Exploit circles complete in ~77 steps (3.5s). In a 30-step window the car
covers only ~40% of one circle — partial arc efficiency ≈ 0.77, well above
the 0.15 threshold. Gate never fired. Car earned positive reward while
circling, outweighing the lap-termination penalty.

Fixes:
  1. window_size: 30 → 200 steps (~9s). Now covers 2+ full exploit circles,
     driving efficiency → 0 and reliably triggering the gate.
  2. min_lap_time: 5.0s → 12.0s. Genuine generated_track laps are 13-16s;
     genuine mountain laps are 27-29s. Anything under 12s is an exploit.
     Episode terminates immediately with large penalty on any sub-12s lap.

Everything else identical to Exp 17.

Setup — TWO sim instances required:
  Sim 1: donkey_sim.exe on port 9091 → generated_track
  Sim 2: separate copy of donkey_sim.exe on port 9093 → mountain_track
"""
import sys, os, time
sys.path.insert(0, '/home/paulh/projects/donkeycar-rl-autoresearch/agent')

from multitrack_runner import log, StuckTerminationWrapper
from donkeycar_sb3_runner import ThrottleClampWrapper
from reward_wrapper import SpeedRewardWrapper
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv, VecTransposeImage
import gymnasium as gym
import numpy as np

HOST             = 'localhost'
THROTTLE_MIN     = 0.2
LR               = 0.000725
TOTAL_STEPS      = 450_000
CHECKPOINT_EVERY = 20_000
SAVE_DIR         = '/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/exp18-parallel-450k-v2'
os.makedirs(SAVE_DIR, exist_ok=True)

# Exploit fixes: larger window catches full circles; higher min_lap_time
# kills sub-genuine laps before they can contribute positive reward.
EFFICIENCY_WINDOW = 200   # was 30 — now covers 2+ exploit circles at 22fps
MIN_LAP_TIME      = 12.0  # was 5.0 — genuine laps: gentrack 13-16s, mountain 27-29s


def make_env(track_id, port):
    def _init():
        raw = gym.make(track_id, conf={'host': HOST, 'port': port})
        env = ThrottleClampWrapper(raw, throttle_min=THROTTLE_MIN)
        env = StuckTerminationWrapper(env, stuck_steps=40, min_displacement=0.5)
        env = SpeedRewardWrapper(env, window_size=EFFICIENCY_WINDOW, min_lap_time=MIN_LAP_TIME)
        return env
    return _init


log('=' * 60)
log('Exp 18: Parallel DummyVecEnv — 450k steps (exploit fix v2)')
log(f'  Sim 1: {HOST}:9091 → generated_track')
log(f'  Sim 2: {HOST}:9093 → mountain_track')
log(f'  throttle_min={THROTTLE_MIN}, lr={LR}, total={TOTAL_STEPS:,}')
log(f'  Reward: v6 + exploit fix (window={EFFICIENCY_WINDOW}, min_lap={MIN_LAP_TIME}s)')
log(f'  Stuck termination: 40 steps (~2.5s)')
log(f'  Checkpoints: every {CHECKPOINT_EVERY:,} steps')
log('=' * 60)

log('Creating DummyVecEnv with two tracks...')
env = DummyVecEnv([
    make_env('donkey-generated-track-v0', 9091),
    make_env('donkey-mountain-track-v0', 9093),
])
env = VecTransposeImage(env)
log(f'  VecEnv num_envs={env.num_envs}, obs={env.observation_space.shape}')

model = PPO('CnnPolicy', env, learning_rate=LR, verbose=1, device='cpu')
log('PPO created. Starting training...')

best_reward = float('-inf')
steps_done = 0

while steps_done < TOTAL_STEPS:
    seg_steps = min(CHECKPOINT_EVERY, TOTAL_STEPS - steps_done)
    model.learn(total_timesteps=seg_steps, reset_num_timesteps=False)
    steps_done += seg_steps

    ckpt = os.path.join(SAVE_DIR, f'checkpoint_{steps_done:07d}')
    model.save(ckpt)
    model.save(os.path.join(SAVE_DIR, 'model'))
    log(f'[{steps_done:,}/{TOTAL_STEPS:,}] Checkpoint saved: {ckpt}.zip')

    # Eval on both training tracks using the existing DummyVecEnv connections
    try:
        obs = env.reset()
        ep_rewards = np.zeros(env.num_envs)
        ep_steps   = np.zeros(env.num_envs)
        done_mask  = np.zeros(env.num_envs, dtype=bool)
        for _ in range(2000):
            action, _ = model.predict(obs, deterministic=True)
            obs, rewards, dones, infos = env.step(action)
            for i in range(env.num_envs):
                if not done_mask[i]:
                    ep_rewards[i] += rewards[i]
                    ep_steps[i]   += 1
                    if dones[i]:
                        done_mask[i] = True
            if done_mask.all():
                break

        status0 = '✅' if ep_steps[0] >= 2000 else f'❌@{int(ep_steps[0])}'
        status1 = '✅' if ep_steps[1] >= 2000 else f'❌@{int(ep_steps[1])}'
        log(f'  Eval: gen_track={ep_rewards[0]:.1f}r/{int(ep_steps[0])}s {status0}  '
            f'mountain={ep_rewards[1]:.1f}r/{int(ep_steps[1])}s {status1}')

        total_reward = ep_rewards.sum()
        if total_reward > best_reward:
            best_reward = total_reward
            model.save(os.path.join(SAVE_DIR, 'best_model'))
            log(f'  ⭐ NEW BEST: {best_reward:.1f} combined reward')
    except Exception as e:
        log(f'  Eval error: {e}')
        import traceback; traceback.print_exc()

model.save(os.path.join(SAVE_DIR, 'model'))
log(f'\nTraining complete. Best combined reward: {best_reward:.1f}')

env.close()
time.sleep(5)

# --- Final eval on all 4 tracks (sequential, port 9091) ---
log('\n' + '=' * 60)
log('FINAL EVALUATION: best_model on 4 tracks (3 sets each)')
log('=' * 60)

EVAL_TRACKS = [
    ('donkey-generated-track-v0',  'generated_track'),
    ('donkey-mountain-track-v0',   'mountain_track'),
    ('donkey-minimonaco-track-v0', 'mini_monaco'),
    ('donkey-generated-roads-v0',  'generated_road'),
]
EVAL_PORT     = 9091
EVAL_SETS     = 3
EVAL_MAX_STEPS = 2000

best_model_path  = os.path.join(SAVE_DIR, 'best_model.zip')
results_by_track = {}

for track_id, track_name in EVAL_TRACKS:
    log(f'\n--- {track_name} ---')
    steps_list = []

    for s in range(1, EVAL_SETS + 1):
        try:
            raw       = gym.make(track_id, conf={'host': HOST, 'port': EVAL_PORT})
            inner     = ThrottleClampWrapper(raw, throttle_min=THROTTLE_MIN)
            inner     = StuckTerminationWrapper(inner, stuck_steps=40, min_displacement=0.5)
            inner     = SpeedRewardWrapper(inner)
            eval_env  = VecTransposeImage(DummyVecEnv([lambda e=inner: e]))

            eval_model = PPO.load(best_model_path, env=eval_env, device='cpu')

            obs = eval_env.reset()
            total_r, total_s, done = 0.0, 0, False
            while not done and total_s < EVAL_MAX_STEPS:
                action, _ = eval_model.predict(obs, deterministic=True)
                result = eval_env.step(action)
                if len(result) == 4:
                    obs, r, d, info = result
                    done = bool(d[0])
                else:
                    obs, r, t, tr, info = result
                    done = bool(t[0] or tr[0])
                total_r += float(r[0])
                total_s += 1

            status = '✅' if total_s >= EVAL_MAX_STEPS else f'❌@{total_s}'
            log(f'  Set {s}: {total_r:.1f}r / {total_s}s {status}')
            steps_list.append(total_s)

            eval_env.close()
            time.sleep(3)
        except Exception as e:
            log(f'  Set {s}: ERROR — {e}')
            steps_list.append(0)
            time.sleep(3)

    mean_steps = np.mean(steps_list) if steps_list else 0
    results_by_track[track_name] = steps_list
    log(f'  Mean: {mean_steps:.0f} steps')

log('\n' + '=' * 60)
log('SUMMARY')
log('=' * 60)
for track_name, steps_list in results_by_track.items():
    steps_str = '/'.join(str(s) for s in steps_list)
    mean      = np.mean(steps_list)
    verdict   = '✅' if mean >= 1500 else '⚠️' if mean >= 500 else '❌'
    log(f'  {verdict} {track_name:20s}: {steps_str}  mean={mean:.0f}')

log(f'\n=== Exp 17 COMPLETE ===')