DQN playing Acrobot-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/2067e21d62fff5db60168687e7d9e89019a8bfc0
79943a9
| ALGO="ppo" | |
| ENVS="HalfCheetahBulletEnv-v0 AntBulletEnv-v0 HopperBulletEnv-v0 Walker2DBulletEnv-v0" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| bash scripts/train_loop.sh -a $ALGO -e "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD |