DQN playing Acrobot-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/1d4094fbcc9082de7f53f4348dd4c7c354152907
16eb59e
| 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 |