DQN playing QbertNoFrameskip-v4 from https://github.com/sgoodfriend/rl-algo-impls/tree/e8bc541d8b5e67bb4d3f2075282463fb61f5f2c6
f540c0e
| source benchmarks/train_loop.sh | |
| # export WANDB_PROJECT_NAME="rl-algo-impls" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-6}" | |
| ALGOS=( | |
| # "vpg" | |
| # "dqn" | |
| "ppo" | |
| ) | |
| ENVS=( | |
| # Basic | |
| "CartPole-v1" | |
| "MountainCar-v0" | |
| "MountainCarContinuous-v0" | |
| "Acrobot-v1" | |
| "LunarLander-v2" | |
| # PyBullet | |
| "HalfCheetahBulletEnv-v0" | |
| "AntBulletEnv-v0" | |
| "HopperBulletEnv-v0" | |
| "Walker2DBulletEnv-v0" | |
| # CarRacing | |
| "CarRacing-v0" | |
| # Atari | |
| "PongNoFrameskip-v4" | |
| "BreakoutNoFrameskip-v4" | |
| "SpaceInvadersNoFrameskip-v4" | |
| "QbertNoFrameskip-v4" | |
| ) | |
| train_loop "${ALGOS[*]}" "${ENVS[*]}" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD | |