PPO playing Acrobot-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/5598ebc4b03054f16eebe76792486ba7bcacfc5c
341188c
| source benchmarks/train_loop.sh | |
| ALGOS="ppo" | |
| ENVS="HalfCheetahBulletEnv-v0 AntBulletEnv-v0 Walker2DBulletEnv-v0 HopperBulletEnv-v0" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| train_loop $ALGOS "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD |