DQN playing QbertNoFrameskip-v4 from https://github.com/sgoodfriend/rl-algo-impls/tree/e8bc541d8b5e67bb4d3f2075282463fb61f5f2c6
f540c0e
| source benchmarks/train_loop.sh | |
| ALGOS="ppo" | |
| ENVS="PongNoFrameskip-v4 BreakoutNoFrameskip-v4" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| train_loop $ALGOS "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD |